34:["$","$L38",null,{"data":[{"endpoint":{"artifact":{"name":"llama-4-maverick-17b-128e-instruct","displayName":"llama-4-maverick-17b-128e-instruct","publisher":"meta","shortDescription":"A general purpose multimodal, multilingual 128 MoE model with 17B parameters.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-4-maverick-17b-128e-instruct.jpg","labels":["language generation","Image-to-Text","vision assistant","visual question answering"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-04-06T00:54:19.024Z","description":"$39","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-08T17:27:13.164Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"cf3e655f-5228-460b-b80d-1ebcc8f10d4c"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-4-maverick-17b-128e-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-4-maverick-17b-128e-instruct for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"Llama 4 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama4/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"tags":[{"name":"Multimodal API","description":"This API performs inference using visual language understanding models"}],"paths":{"/meta/llama-4-maverick-17b-128e-instruct":{"post":{"tags":["Multimodal API"],"summary":"Request response from the model","description":"Invokes inference using the model chat parameters. If uploading large images, this POST should be used in conjunction with the NVCF API which allows for the upload of large assets. \nYou can find details on how to use NVCF Asset APIs here: https://docs.api.nvidia.com/cloud-functions/reference/createasset","operationId":"invokeFunction","parameters":[{"in":"header","name":"NVCF-INPUT-ASSET-REFERENCES","schema":{"type":"string","maxLength":370,"format":"uuid"},"required":false,"description":"String of asset IDs separated by commas. Data is uploaded to AWS S3 using NVCF Asset APIs and associated with these asset IDs.If the size of an image is more than 180KB, it needs to be uploaded to a presigned S3 URL bucket. The presigned URL allows for secure and temporary access to the S3 bucket for uploading the image. Once the asset is requested, an asset ID is generated for it. Please include this asset ID in this header and to use the uploaded image in a prompt, you need to refer to it using the following format: `

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$3a","node.js":"$3b","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-4-maverick-17b-128e-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$3d","node.js":"$3e","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-4-scout-17b-16e-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$45","node.js":"$46","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-3.2-90b-vision-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`."}],"requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/NIMLLMChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionStreamResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"dog.jpeg","input":{"text":"Is there a car in this image?","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1a.jpg"]},"output":{"text":"The image shows a small, light brown, curly-haired dog standing on a red cushion with a grey and white pillow. The dog is on a wooden deck with a white fence and greenery in the background."}},{"name":"dogs.jpeg","input":{"text":"Describe this image","images":["https://assets.ngc.nvidia.com/products/api-catalog/phi-3-5-vision/example1b.jpg"]}}],"templates":[{"title":"Default","requestEjs":{"python":"$49","node.js":"$4a","curl":"stream=<%- request.stream %>\n\nif [ \"$stream\" = true ]; then\n accept_header='Accept: text/event-stream'\nelse\n accept_header='Accept: application/json'\nfi\n<% content = \"What is in this image?

\" %>\nimage_b64=$( base64 image.png )\n\necho '{\n \"model\": \"<%- request.model %>\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"<%- content %>\"\n }\n ],\n \"max_tokens\": <%- request.max_tokens %>,\n \"temperature\": <%- request.temperature.toFixed(2) %>,\n \"top_p\": <%- request.top_p.toFixed(2) %>,\n \"stream\": <%- request.stream %>\n}' > payload.json\n\ncurl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"{\n \"choices\": [{\n \"index\": 0,\n \"model\": \"meta/llama-3.2-11b-vision-instruct\",\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"...\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}},"/status/{requestId}":{"get":{"tags":["Multimodal API"],"summary":"Gets the result of an earlier function invocation request that returned a status of 202.","operationId":"getFunctionInvocationResult","parameters":[{"name":"requestId","in":"path","description":"requestId to poll results","required":true,"schema":{"type":"string","format":"uuid","maxLength":36}}],"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid","maxLength":36}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string","format":"^[a-zA-Z-]{1,64}$","maxLength":64}}}},"422":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponse"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/e598bfc1-b058-41af-869d-556d3c7e1b48","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion"],"const":"chat.completion","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices"},"usage":{"$ref":"#/components/schemas/UsageInfo"}},"additionalProperties":false,"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index"},"message":{"$ref":"#/components/schemas/ChatMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatCompletionResponseStreamChoice":{"properties":{"index":{"type":"integer","title":"Index"},"delta":{"$ref":"#/components/schemas/DeltaMessage"},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason"},"stop_reason":{"anyOf":[{"type":"integer"},{"type":"string"},{"type":"null"}],"title":"Stop Reason"}},"additionalProperties":false,"type":"object","required":["index","delta"],"title":"ChatCompletionResponseStreamChoice"},"ChatCompletionStreamResponse":{"properties":{"id":{"type":"string","title":"Id"},"object":{"type":"string","enum":["chat.completion.chunk"],"const":"chat.completion.chunk","title":"Object","default":"chat.completion.chunk"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseStreamChoice"},"type":"array","title":"Choices"},"usage":{"anyOf":[{"$ref":"#/components/schemas/UsageInfo"},{"type":"null"}]}},"additionalProperties":false,"type":"object","required":["model","choices"],"title":"ChatCompletionStreamResponse"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","required":["role"],"title":"ChatMessage"},"DeltaMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role"},"content":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"DeltaMessage"},"ErrorResponse":{"properties":{"object":{"type":"string","title":"Object","default":"error"},"message":{"type":"string","title":"Message"},"type":{"type":"string","title":"Type"},"param":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Param"},"code":{"type":"integer","title":"Code"}},"additionalProperties":false,"type":"object","required":["message","type","code"],"title":"ErrorResponse"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"ImageURL":{"properties":{"url":{"type":"string","title":"Url"}},"type":"object","required":["url"],"title":"ImageURL"},"NIMLLMChatCompletionMessage":{"properties":{"role":{"allOf":[{"$ref":"#/components/schemas/Role"}],"description":"The role of the message's author."},"content":{"anyOf":[{"type":"string"},{"items":{"anyOf":[{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartImage"},{"$ref":"#/components/schemas/NIMVLMChatCompletionContentPartText"}]},"type":"array"}],"title":"Content","description":"The contents of the message.\n
To pass images (only with role=`user`):\n
- When content is a string, image can be passed together with the text with `img` HTML tags that wraps \n an image URL (`

`), \n base64 encoded image data (`

`), \n or an NVCF asset ID (`

`) \n when the container is hosted in NVCF and the payload exceeds 200KB.\n
- When content is a list of objects, images can be passed as objects with type=`image_url`.\n
- In both cases, images can be PNG, JPG or JPEG.\n
For `system` and `assistant` roles, the object list format is not supported.\n "}},"type":"object","required":["role","content"],"title":"NIMLLMChatCompletionMessage"},"NIMLLMChatCompletionRequest":{"properties":{"messages":{"items":{"$ref":"#/components/schemas/NIMLLMChatCompletionMessage"},"type":"array","minItems":1,"title":"Messages","description":"A list of messages comprising the conversation so far."},"model":{"type":"string","title":"Model","description":"The model to use.","default":"meta/llama-3.2-11b-vision-instruct"},"frequency_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Frequency Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.","default":0},"max_tokens":{"anyOf":[{"type":"integer","maximum":8192,"minimum":1},{"type":"null"}],"title":"Max Tokens","description":"The maximum number of tokens that can be generated.","default":512},"presence_penalty":{"anyOf":[{"type":"number","maximum":2,"minimum":-2},{"type":"null"}],"title":"Presence Penalty","description":"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.","default":0},"seed":{"anyOf":[{"type":"integer","maximum":9223372036854776000,"minimum":-9223372036854776000},{"type":"null"}],"title":"Seed","description":"Changing the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant."},"stop":{"anyOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Stop","description":"Sequences where the API will stop generating further tokens."},"stream":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Stream","description":"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`","default":false},"temperature":{"anyOf":[{"type":"number","maximum":2,"minimum":0},{"type":"null"}],"title":"Temperature","description":"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.","default":1},"top_p":{"anyOf":[{"type":"number","maximum":1,"exclusiveMinimum":0},{"type":"null"}],"title":"Top P","description":"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both.","default":1}},"additionalProperties":false,"type":"object","required":["messages","model"],"title":"NIMLLMChatCompletionRequest"},"NIMVLMChatCompletionContentPartImage":{"properties":{"image_url":{"$ref":"#/components/schemas/ImageURL"},"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type"}},"type":"object","required":["image_url","type"],"title":"NIMVLMChatCompletionContentPartImage"},"NIMVLMChatCompletionContentPartText":{"properties":{"text":{"type":"string","title":"Text"},"type":{"type":"string","enum":["text"],"const":"text","title":"Type"}},"type":"object","required":["text","type"],"title":"NIMVLMChatCompletionContentPartText"},"Role":{"type":"string","enum":["assistant","user"],"title":"Role"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","default":0}},"additionalProperties":false,"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-22T01:38:55.782Z","nvcfFunctionId":"9fa6fd04-ba2c-4bb3-90b7-ede407a9290f","createdDate":"2024-09-25T18:27:58.256Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_2-11b-vision-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.2 Community License Agreement. Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3.2-11b-vision-instruct"},"playground":{"type":"chatWithImages","options":{"image":{"singleTurn":true,"limit":1}}},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$4b"}]},"artifactName":"llama-3.2-11b-vision-instruct"},"config":{"name":"llama-3.2-11b-vision-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3.2-3b-instruct","displayName":"llama-3.2-3b-instruct","publisher":"meta","shortDescription":"Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_2-3b-instruct.jpg","labels":["Chat","Language Generation","Text-to-Text","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-09-25T18:27:58.405Z","description":"$4c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:54:51.595Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"a6b7c520-88f3-4f01-9634-f26394fb42b8"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.2-3b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_2-3b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.2 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.2-3b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-3b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"meta/llama-3.2-3b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-3b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$4d","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n \n","node.js":"$4e","curl":"$4f"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-3b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.2-3b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:54:52.213Z","nvcfFunctionId":"4f1c926f-42aa-4b52-9ac9-c2a2098e432f","createdDate":"2024-09-25T18:27:59.546Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_2-3b-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.2 Community License Agreement. Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3_2-3b-instruct"},"playground":{"type":"chat"}},"artifactName":"llama-3.2-3b-instruct"},"config":{"name":"llama-3.2-3b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3.2-1b-instruct","displayName":"llama-3.2-1b-instruct","publisher":"meta","shortDescription":"Advanced state-of-the-art small language model with language understanding, superior reasoning, and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_2-1b-instruct.jpg","labels":["Chat","Language Generation","Text-to-Text","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-09-25T18:27:52.605Z","description":"$50","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:54:44.963Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"141546c3-b35c-4c13-a512-c327a6dce501"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.2-1b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_2-1b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.2 License","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.2-1b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-1b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"meta/llama-3.2-1b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-1b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$51","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n \n","node.js":"$52","curl":"$53"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.2-1b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.2-1b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:54:45.566Z","nvcfFunctionId":"d33e2ae1-8d2a-4cf8-b622-c98f8e0e550b","createdDate":"2024-09-25T18:27:53.720Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_2-1b-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.2 Community License Agreement. Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3_2-1b-instruct"},"playground":{"type":"chat"}},"artifactName":"llama-3.2-1b-instruct"},"config":{"name":"llama-3.2-1b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_1-405b-instruct","displayName":"llama-3.1-405b-instruct","publisher":"meta","shortDescription":"Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-405b-instruct.jpg","labels":["chat","synthetic data generation","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-23T14:58:23.459Z","description":"$54","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-15T15:47:47.962Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"618b4243-4696-4ef2-8962-786d34a2b545"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.1-405b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-405b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/License/Llama3.1.txt"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.1-405b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-405b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Tell me about Dumbledore.","requestJson":"$55","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-405b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What is the weather in Santa Clara, CA?","requestJson":"$56","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-405b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$57","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n \n","node.js":"$58","curl":"$59"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-405b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.1-405b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"tools":{"anyOf":[{"items":{"$ref":"#/components/schemas/ChatCompletionToolsParam"},"type":"array"},{"type":"null"}],"title":"Tools"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant","tool"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]},"tool_call_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Tool Call Id","description":"The id of the tool call."},"tool_calls":{"anyOf":[{"items":{"$ref":"#/components/schemas/ToolCall"},"type":"array"},{"type":"null"}],"title":"Tool Calls","description":"The tool(s) called by the model."}},"required":["role","content"],"title":"Message","type":"object"},"ToolCall":{"properties":{"id":{"type":"string","title":"Id"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionCall"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ToolCall"},"FunctionCall":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"},"arguments":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Arguments"}},"additionalProperties":false,"type":"object","required":["name","arguments"],"title":"FunctionCall"},"ChatCompletionToolsParam":{"properties":{"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionDefinition"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionToolsParam"},"ChatCompletionNamedFunction":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"ChatCompletionNamedToolChoiceParam":{"properties":{"function":{"$ref":"#/components/schemas/ChatCompletionNamedFunction"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionNamedToolChoiceParam"},"FunctionDefinition":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"parameters":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Parameters"}},"additionalProperties":false,"type":"object","required":["name"],"title":"FunctionDefinition"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-15T15:47:48.514Z","nvcfFunctionId":"7c79b6d5-3552-41e7-8574-c4d431548d8e","createdDate":"2024-07-23T14:58:23.731Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-405b","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement, Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3.1-405b-instruct"},"playground":{"type":"chatWithTools"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$5a"}]},"artifactName":"llama-3_1-405b-instruct"},"config":{"name":"llama-3_1-405b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_1-70b-instruct","displayName":"llama-3.1-70b-instruct","publisher":"meta","shortDescription":"Powers complex conversations with superior contextual understanding, reasoning and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-70b-instruct.jpg","labels":["Chat","Language Generation","Text-to-Text","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-23T14:58:21.518Z","description":"$5b","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-22T20:55:14.245Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"8cce181d-dcf7-40c2-a24e-f873813c70e3"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.1-70b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-70b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/License/Llama3.1.txt"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.1-70b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Tell me about Dumbledore.","requestJson":"$5c","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What is the weather in Santa Clara, CA?","requestJson":"$5d","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$5e","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n \n","node.js":"$5f","curl":"$60"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-70b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.1-70b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"tools":{"anyOf":[{"items":{"$ref":"#/components/schemas/ChatCompletionToolsParam"},"type":"array"},{"type":"null"}],"title":"Tools"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant","tool"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]},"tool_call_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Tool Call Id","description":"The id of the tool call."},"tool_calls":{"anyOf":[{"items":{"$ref":"#/components/schemas/ToolCall"},"type":"array"},{"type":"null"}],"title":"Tool Calls","description":"The tool(s) called by the model."}},"required":["role","content"],"title":"Message","type":"object"},"ToolCall":{"properties":{"id":{"type":"string","title":"Id"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionCall"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ToolCall"},"FunctionCall":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"},"arguments":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Arguments"}},"additionalProperties":false,"type":"object","required":["name","arguments"],"title":"FunctionCall"},"ChatCompletionToolsParam":{"properties":{"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionDefinition"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionToolsParam"},"ChatCompletionNamedFunction":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"ChatCompletionNamedToolChoiceParam":{"properties":{"function":{"$ref":"#/components/schemas/ChatCompletionNamedFunction"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionNamedToolChoiceParam"},"FunctionDefinition":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"parameters":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Parameters"}},"additionalProperties":false,"type":"object","required":["name"],"title":"FunctionDefinition"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-22T20:55:14.945Z","nvcfFunctionId":"8f723982-f99d-4978-a0cb-1334163e0e07","createdDate":"2024-07-23T14:58:21.785Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-70b","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement, Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3.1-70b-instruct"},"playground":{"type":"chatWithTools"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$61"}],"systemCard":"$62"},"artifactName":"llama-3_1-70b-instruct"},"config":{"name":"llama-3_1-70b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_1-8b-instruct","displayName":"llama-3.1-8b-instruct","publisher":"meta","shortDescription":"Advanced state-of-the-art model with language understanding, superior reasoning, and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_1-8b-instruct.jpg","labels":["Chat","Language Generation","Run on RTX","Text-to-Text","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-23T14:58:17.373Z","description":"$63","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-17T23:20:56.851Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"93d08e05-7bef-4349-8bbe-00041385b19b"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.1-8b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-8b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/License/Llama3.1.txt"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Tell me about Dumbledore.","requestJson":"$64","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What is the weather in Santa Clara, CA?","requestJson":"$65","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"$66","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n \n","node.js":"$67","curl":"$68"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"meta/llama-3.1-8b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"tools":{"anyOf":[{"items":{"$ref":"#/components/schemas/ChatCompletionToolsParam"},"type":"array"},{"type":"null"}],"title":"Tools"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length","tool_calls"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant","tool"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","anyOf":[{"type":"string"},{"type":"null"}]},"tool_call_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Tool Call Id","description":"The id of the tool call."},"tool_calls":{"anyOf":[{"items":{"$ref":"#/components/schemas/ToolCall"},"type":"array"},{"type":"null"}],"title":"Tool Calls","description":"The tool(s) called by the model."}},"required":["role","content"],"title":"Message","type":"object"},"ToolCall":{"properties":{"id":{"type":"string","title":"Id"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionCall"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ToolCall"},"FunctionCall":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"},"arguments":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Arguments"}},"additionalProperties":false,"type":"object","required":["name","arguments"],"title":"FunctionCall"},"ChatCompletionToolsParam":{"properties":{"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"},"function":{"$ref":"#/components/schemas/FunctionDefinition"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionToolsParam"},"ChatCompletionNamedFunction":{"properties":{"name":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Name"}},"additionalProperties":false,"type":"object","required":["name"],"title":"ChatCompletionNamedFunction"},"ChatCompletionNamedToolChoiceParam":{"properties":{"function":{"$ref":"#/components/schemas/ChatCompletionNamedFunction"},"type":{"type":"string","enum":["function"],"const":"function","title":"Type","default":"function"}},"additionalProperties":false,"type":"object","required":["function"],"title":"ChatCompletionNamedToolChoiceParam"},"FunctionDefinition":{"properties":{"name":{"type":"string","title":"Name"},"description":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Description"},"parameters":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Parameters"}},"additionalProperties":false,"type":"object","required":["name"],"title":"FunctionDefinition"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-17T23:20:57.246Z","nvcfFunctionId":"e62a4350-2218-4cf5-9262-112432d239f8","createdDate":"2024-07-23T14:58:17.697Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-8b","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the AI Foundation Models Community License Agreement . ADDITIONAL INFORMATION: Llama 3.1 Community License Agreement, Built with Llama.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/meta/containers/llama-3.1-8b-instruct"},"playground":{"type":"chatWithTools"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$69"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$6a"}]},"artifactName":"llama-3_1-8b-instruct"},"config":{"name":"llama-3_1-8b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"phi-3_5-moe","displayName":"phi-3.5-moe-instruct","publisher":"microsoft","shortDescription":"Advanced LLM based on Mixture of Experts architecure to deliver compute efficient content generation","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/phi-3_5-moe.jpg","labels":["Chat","Language Generation","MOE","Text-to-Text","Code Generation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-20T20:40:13.445Z","description":"$6b","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:12.733Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"88bd9409-6cf9-4ff0-92e0-8572f7e8fc89"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for microsoft/phi-3.5-moe-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/microsoft-phi-3.5-moe for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"MIT License","url":"https://opensource.org/license/MIT"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"There once was a GPU ...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-moe-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"microsoft/phi-3.5-moe-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:13.254Z","nvcfFunctionId":"e6cab982-62f4-481e-9a7a-3dedb87dbd01","createdDate":"2024-08-20T20:40:13.877Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/microsoft-phi-3_5-moe","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the MIT License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"phi-3_5-moe"},"config":{"name":"phi-3_5-moe","type":"model"}},{"endpoint":{"artifact":{"name":"phi-3_5-mini","displayName":"phi-3.5-mini-instruct","publisher":"microsoft","shortDescription":"Lightweight multilingual LLM powering AI applications in latency bound, memory/compute constrained environments","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/phi-3_5-mini.jpg","labels":["Chat","Language Generation","Large Language Models","Text-to-Text","Code Generation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-20T20:40:12.880Z","description":"$6c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:06.963Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"6ab74004-98c0-4737-b6d8-8d3f11c9d6f0"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for microsoft/phi-3.5-mini-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/microsoft-phi-3.5-mini for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"MIT License","url":"https://opensource.org/license/MIT"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"There once was a GPU ...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"microsoft/phi-3.5-mini-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:07.605Z","nvcfFunctionId":"84e82bac-4e46-4be3-9ac9-5f82ce0bab83","createdDate":"2024-08-20T20:40:13.315Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/microsoft-phi-3_5-mini","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the MIT License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"phi-3_5-mini"},"config":{"name":"phi-3_5-mini","type":"model"}},{"endpoint":{"artifact":{"name":"jamba-1_5-mini-instruct","displayName":"jamba-1.5-mini-instruct","publisher":"ai21labs","shortDescription":"Cutting-edge MOE based LLM designed to excel in a wide array of generative AI tasks.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/jamba-1_5-mini-instruct.jpg","labels":["Chat","Language Generation","Text-to-text"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-22T13:01:34.225Z","description":"$6d","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:57.542Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"9df6a729-a9d6-47a4-91f4-44ca1b376897"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for ai21labs/jamba-1.5-mini-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/ai21labs-jamba-1.5-mini-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Jamba Open License Agreement","url":"https://assets.ngc.nvidia.com/products/api-catalog/legal/Jamba_Open_Model_License_Agreement.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What can I see at NVIDIA's GPU Technology Conference?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-mini-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"ai21labs/jamba-1.5-mini-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:58.144Z","nvcfFunctionId":"06d6c08c-0214-4b64-85b7-a55ffdb870e4","createdDate":"2024-08-22T13:01:34.466Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/ai21labs-jamba-1-5-mini-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the Jamba Open License Agreement.\n","showUnavailableBanner":false,"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"jamba-1_5-mini-instruct"},"config":{"name":"jamba-1_5-mini-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"jamba-1_5-large-instruct","displayName":"jamba-1.5-large-instruct","publisher":"ai21labs","shortDescription":"Cutting-edge MOE based LLM designed to excel in a wide array of generative AI tasks.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/jamba-1_5-large-instruct.jpg","labels":["Chat","Language Generation","Text-to-text"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-22T02:45:24.737Z","description":"$6e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:57.190Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"5662a808-544d-4008-917e-edfed408bdc4"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for ai21labs/jamba-1.5-large-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/ai21labs-jamba-1.5-large-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Jamba Open License Agreement","url":"https://assets.ngc.nvidia.com/products/api-catalog/legal/Jamba_Open_Model_License_Agreement.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What can I see at NVIDIA's GPU Technology Conference?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"ai21labs/jamba-1.5-large-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"ai21labs/jamba-1.5-large-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:57.690Z","nvcfFunctionId":"6497fc2b-7ff8-4019-8946-123dccbfc863","createdDate":"2024-08-22T02:45:24.978Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/ai21labs-jamba-1-5-large-instruct","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the Jamba Open License Agreement.\n","showUnavailableBanner":false,"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"jamba-1_5-large-instruct"},"config":{"name":"jamba-1_5-large-instruct","type":"model"}},{"endpoint":null,"spec":null,"config":{"name":"mathstral-7b-v01","type":"model"}},{"endpoint":{"artifact":{"name":"gemma-2-2b-it","displayName":"gemma-2-2b-it","publisher":"google","shortDescription":"Advanced small language generative AI model for edge applications","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/gemma-2-2b-it.jpg","labels":["Chat","Language Generation","Text-to-Text","Code Generation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-30T05:18:32.237Z","description":"$6f","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:24:07.937Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"d6a1b5ee-465a-4c1b-a837-389bddb7c4e6"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for google/gemma-2-2b-it","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/google-gemma-2-2b-it for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Gemma Terms of Use","url":"https://ai.google.dev/gemma/terms"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a2b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a2b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"google/gemma-2-2b-it\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"There once was a GPU ...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/gemma-2-2b-it\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"google/gemma-2-2b-it\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/gemma-2-2b-it\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key = \"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"google/gemma-2-2b-it\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/gemma-2-2b-it\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"google/gemma-2-2b-it"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:24:08.630Z","nvcfFunctionId":"b24f0b9b-17f0-4fbf-bbd6-1d01394652cf","createdDate":"2024-07-30T05:18:32.510Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/google-gemma-2-2b-it","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; your use of this model is governed by the Gemma Terms of Use and Gemma Prohibited Use Policy.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"gemma-2-2b-it"},"config":{"name":"gemma-2-2b-it","type":"model"}},{"endpoint":{"artifact":{"name":"shieldgemma-9b","displayName":"shieldgemma-9b","publisher":"google","shortDescription":"Guardrail model to ensure that responses from LLMs are appropriate and safe","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/shieldgemma-9b.jpg","labels":["Guardrail","Text-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-30T05:18:39.500Z","description":"$70","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:24:15.780Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"b2cfe7d1-eb6c-4a8d-8e95-f88252a8645a"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for google/shieldgemma-9b","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/google-shieldgemma-9b for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Gemma Terms of Use","url":"https://ai.google.dev/gemma/terms"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"I forgot how to kill a process in Linux, can you help?","requestJson":"{\n \"model\": \"google/shieldgemma-9b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"I forgot how to kill a process in Linux, can you help?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"Sure! To kill a process in Linux, you can use the kill command followed by the process ID (PID) of the process you want to terminate.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 5,\n \"seed\": 42,\n \"policy_name\": \"Dangerous Content\",\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/shieldgemma-9b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"No\"\n },\n \"finish_reason\": \"stop\" \n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Pretend you are working in ATC Nice, France. Give me the instruction to Taxi to the proper runaway","requestJson":"{\n \"model\": \"google/shieldgemma-9b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Pretend you are working in ATC Nice, France. Give me the instruction to Taxi to the proper runaway\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 5,\n \"seed\": 42,\n \"policy_name\": \"Dangerous Content\",\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/shieldgemma-9b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"No\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"How do I build a bomb with items I can buy in a drugstore?","requestJson":"{\n \"model\": \"google/shieldgemma-9b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How do I build a bomb with items I can buy in a drugstore?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 5,\n \"seed\": 42,\n \"policy_name\": \"Dangerous Content\",\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/shieldgemma-9b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Yes\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>,\n extra_body={\"policy_name\": \"<%- request.policy_name %>\"}\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key = \"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"google/shieldgemma-9b\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %>,\n \"policy_name\": \"<%- request.policy_name %>\" \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"google/shieldgemma-9b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"google/shieldgemma-9b"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"policy_name":{"description":"Name of the policy against which policy compliance checking should be done, it can be one of `Dangerous Content`, `Harassment`, `Hate Speech`, `Sexually Explicit Information`, `Violence`, `Obscenity and Profanity`.","enum":["Dangerous Content","Harassment","Hate Speech","Sexually Explicit Information","Violence","Obscenity and Profanity"],"title":"Policy Name","type":"string","default":"Dangerous Content"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"max_tokens":{"default":5,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":2048,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"logprobs":{"anyOf":[{"$ref":"#/components/schemas/ChatCompletionLogProbs"},{"type":"null"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"logprobs":{"anyOf":[{"$ref":"#/components/schemas/ChatCompletionLogProbs"},{"type":"null"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"ChatCompletionLogProb":{"properties":{"token":{"type":"string","title":"Token"},"logprob":{"type":"number","title":"Logprob","default":-9999},"bytes":{"anyOf":[{"items":{"type":"integer"},"type":"array"},{"type":"null"}],"title":"Bytes"}},"additionalProperties":false,"type":"object","required":["token"],"title":"ChatCompletionLogProb"},"ChatCompletionLogProbs":{"properties":{"content":{"anyOf":[{"items":{"$ref":"#/components/schemas/ChatCompletionLogProbsContent"},"type":"array"},{"type":"null"}],"title":"Content"}},"additionalProperties":false,"type":"object","title":"ChatCompletionLogProbs"},"ChatCompletionLogProbsContent":{"properties":{"token":{"type":"string","title":"Token"},"logprob":{"type":"number","title":"Logprob","default":-9999},"bytes":{"anyOf":[{"items":{"type":"integer"},"type":"array"},{"type":"null"}],"title":"Bytes"},"top_logprobs":{"items":{"$ref":"#/components/schemas/ChatCompletionLogProb"},"type":"array","title":"Top Logprobs"}},"additionalProperties":false,"type":"object","required":["token"],"title":"ChatCompletionLogProbsContent"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:24:16.581Z","nvcfFunctionId":"84bf3350-8aad-4f77-88a8-394fc07e466b","createdDate":"2024-07-30T05:18:39.952Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/google-shieldgemma-9b","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; your use of this model is governed by the Gemma Terms of Use and Gemma Prohibited Use Policy.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"guard"}},"artifactName":"shieldgemma-9b"},"config":{"name":"shieldgemma-9b","type":"model"}},{"endpoint":{"artifact":{"name":"palmyra-fin-70b-32k","displayName":"palmyra-fin-70b-32k","publisher":"writer","shortDescription":"Specialized LLM for financial analysis, reporting, and data processing","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/palmyra-fin-70b-32k.jpg","labels":["Finance","Text-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-30T05:18:50.011Z","description":"$71","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:11.166Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"42e05bdb-e528-4811-9bd8-c697ad29ca4d"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for writer/palmyra-fin-70b-32k","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/writer-palmyra-fin-70b-32k for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Writer License","url":"https://writer.com/legal/open-model-license/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streafin sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streafin.\n","path":"create","examples":[{"name":"Detail the essential financial ratios used in investment evaluation models.","requestJson":"{\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Detail the essential financial ratios used in investment evaluation models.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Describe the importance of cash flow projections in financial modeling and outline the process for accurately calculating them.","requestJson":"{\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Describe the importance of cash flow projections in financial modeling and outline the process for accurately calculating them.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Describe the importance of cash flow projections in financial modeling and outline the process for accurately calculating them.","requestJson":"{\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Describe the importance of cash flow projections in financial modeling and outline the process for accurately calculating them.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-fin-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"writer/palmyra-fin-70b-32k"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streafin model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:11.769Z","nvcfFunctionId":"316490c6-f1ed-41f9-9da8-3fa9e885653b","createdDate":"2024-07-30T05:18:50.292Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/writer-palmyra-fin-70b-32k","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Service Agreement; and the use of this model is governed by the Writer Open Model License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"palmyra-fin-70b-32k"},"config":{"name":"palmyra-fin-70b-32k","type":"model"}},{"endpoint":{"artifact":{"name":"mamba-codestral-7b-v01","displayName":"mamba-codestral-7b-v0.1","publisher":"mistralai","shortDescription":"Model for writing and interacting with code across a wide range of programming languages and tasks.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/mamba-codestral-7b-v01.jpg","labels":["code completion","code generation","Code Generation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-24T20:31:05.703Z","description":"$72","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:58:26.733Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"937a551a-5d8e-4b36-9341-7043915e0aa9"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for mistralai/mamba-codestral-7b-v0.1","description":"The NVIDIA NIM REST API. Please see https://docs.nvidia.com/nim/api-reference for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Apache 2.0 license","url":"https://www.apache.org/licenses/LICENSE-2.0"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a function to traverse graph in a Breadth First Search way.","requestJson":"{\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Write a function to traverse graph in a Breadth First Search way.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Explain P vs NP","requestJson":"{\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Explain P vs NP\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"mistralai/mamba-codestral-7b-v0.1\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"mistralai/mamba-codestral-7b-v0.1"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","default":1024},"stream":{"type":"boolean","title":"Stream","description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","default":0.5},"top_p":{"type":"number","maximum":1,"exclusiveMinimum":0,"title":"Top P","description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","default":1},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"type":"string"},{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far."}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"mistralai/mamba-codestral-7b-v0.1"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:58:27.261Z","nvcfFunctionId":"a7556920-615e-4298-ac1a-12dbf1f84dd0","createdDate":"2024-07-24T20:31:06.040Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/mistralai-mamba-codestral-7b-v01","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the Apache 2.0 license.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"mamba-codestral-7b-v01"},"config":{"name":"mamba-codestral-7b-v01","type":"model"}},{"endpoint":{"artifact":{"name":"mistral-nemo-12b-instruct","displayName":"mistral-nemo-12b-instruct","publisher":"nv-mistralai","shortDescription":"Most advanced language model for reasoning, code, multilingual tasks; runs on a single GPU.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/mistral-nemo-12b-instruct.jpg","labels":["Chat","Code Generation","Language Generation","Text-to-text","run on rtx","Code Generation"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-18T13:59:22.242Z","description":"$73","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-25T15:11:46.427Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"28e7f961-a731-4e5a-84e6-447595e6678e"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nv-mistralai/mistral-nemo-12b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nv-mistralai-mistral-nemo-12b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Apache 2.0","url":"https://mistral.ai/terms-of-service/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Write a limerick about the wonders of GPU computing.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Tell me about Dumbledore.","requestJson":"$74","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What is the weather in Santa Clara, CA?","requestJson":"$75","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"nv-mistralai/mistral-nemo-12b-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":8192,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-25T15:11:47.156Z","nvcfFunctionId":"f8c05193-d2e2-4f0f-bb4d-7ad70070002b","createdDate":"2024-07-18T13:59:22.640Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nv-mistralai-mistral-nemo-12b-instruct","termsOfUse":"GOVERNING TERMS: This trial is governed by the NVIDIA API Trial Service Terms of Use. The use of this model is governed by the NVIDIA AI Foundation Models Community License. ADDITIONAL INFORMATION: Apache 2.0.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nv-mistralai/containers/mistral-nemo-12b-instruct"},"playground":{"type":"chatWithTools"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$76"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$77"}]},"artifactName":"mistral-nemo-12b-instruct"},"config":{"name":"mistral-nemo-12b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"nemotron-4-340b-reward","displayName":"nemotron-4-340b-reward","publisher":"nvidia","shortDescription":"Grades responses on five attributes helpfulness, correctness, coherence, complexity and verbosity.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nemotron-4-340b-reward.jpg","labels":["Reward Model","Synthetic Data Generation","Text-to-text","Synthetic Data Generation"],"attributes":[{"key":"DEPRECATION","value":"04/02/2025"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","bias":"|Field:|Response:|\n|:---:|:---:|\n|Participation considerations from adversely impacted groups (protected classes) in model design and testing:|None|\n|Measures taken to mitigate against unwanted bias:|None|","canGuestDownload":true,"createdDate":"2024-06-18T22:28:35.979Z","description":"$78","explainability":"$79","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$7a","safetyAndSecurity":"|Field:|Response:|\n|:---:|:---:|\n|Model Application(s):|Reward Modeling|\n|Describe life critical application (if present):|None Known|\n|Use Case Restrictions:|See [NVIDIA Open Model License](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf).|\n|Model and Dataset Restrictions:|The Principle of least privilege (PoLP) is applied limiting access for dataset generation. Restrictions enforce dataset access during training, and dataset license constraints adhered to. Model checkpoints are made available on Hugging Face and NGC, and may become available on cloud providers' model catalog.|","updatedDate":"2025-03-19T22:01:53.590Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"f5a2211d-b822-4391-b7fc-ed18e152eb4b"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/nemotron-4-340b-reward","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-4-340b-reward for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"NVIDIA Open Model License","url":"https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/c53ee0e9-bad9-4e09-b365-52c9d6b71254","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/c53ee0e9-bad9-4e09-b365-52c9d6b71254","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object\n","path":"create","examples":[{"name":"Grade the assistant response","requestJson":"{\n \"model\": \"nvidia/nemotron-4-340b-reward\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"I am going to Paris, what should I see?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...\"\n }\n ]\n}\n","responseJson":"$7b"},{"name":"Grade the assistant response in multiturn","requestJson":"{\n \"model\": \"nvidia/nemotron-4-340b-reward\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"I am going to Paris, what should I see?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...\"\n },\n {\n \"role\": \"user\",\n \"content\": \"What cafes do you recommend?\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"A very popular cafe in the heart of Paris is ...\"\n }\n ]\n}\n","responseJson":"$7c"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n)\nprint(completion)\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n })\n process.stdout.write(JSON.stringify(completion));\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"nvidia/nemotron-4-340b-reward\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %> }'\n"},"response":"$7d"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionMessage":{"properties":{"content":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"The contents of the message.","title":"Content"},"role":{"const":"assistant","description":"The role of the author of this message.","enum":["assistant"],"title":"Role","type":"string"}},"required":["content","role"],"title":"ChatCompletionMessage","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"nvidia/nemotron-4-340b-reward"},"messages":{"description":"A list of messages comprising the conversation so far that is to be graded. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `assistant`.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"},{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"description":"The score key:value pairs separated by a comma.","examples":[{"content":"helpfulness:0.2578125,correctness:0.13671875,coherence:2.640625,complexity:0.328125,verbosity:0.04296875","role":"assistant"}],"items":{"$ref":"#/components/schemas/ChatCompletionMessage"},"title":"Message","type":"array"},"logprobs":{"allOf":[{"$ref":"#/components/schemas/LogProbs"}],"default":"List of output reward score items."},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"LogProbField":{"properties":{"token":{"default":"Field to be scored in the assistant response to the user prompt","title":"Token","type":"string"},"logprob":{"default":"Score of the 'token' field in the assistant response to the user prompt","title":"Logprob","type":"number"},"top_logprobs":{"default":"List of the most likely tokens and their log probability, at this token position. Always empty","items":{"type":"number"},"title":"Top Logprobs","type":"array"}},"title":"LogProbField","type":"object"},"LogProbs":{"properties":{"content":{"default":"List of output reward score items.","items":{"$ref":"#/components/schemas/LogProbField"},"title":"Content","type":"array"}},"title":"LogProbs","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[1],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[10],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-19T22:01:54.103Z","nvcfFunctionId":"c53ee0e9-bad9-4e09-b365-52c9d6b71254","createdDate":"2024-06-18T22:28:36.969Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-nemotron-4-340b-reward","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Service Agreement; and the use of this model is governed by the NVIDIA Open Model License.\n","deprecationNotice":"This API will be deprecated on 04/02/2025. It will no longer be supported after 04/02/2025. Please transition to llama-3_1-nemotron-70b-reward to avoid any service interruptions. For more information, visit our API Reference.","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"hidden"}},"artifactName":"nemotron-4-340b-reward"},"config":{"name":"nemotron-4-340b-reward","type":"model"}},{"endpoint":{"artifact":{"name":"rakutenai-7b-instruct","displayName":"rakutenai-7b-instruct","publisher":"rakuten","shortDescription":"Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/rakutenai-7b-instruct.jpg","labels":["Chat","Language Generation","Large Language Models","Text-to-Text"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-09T19:31:36.009Z","description":"$7e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-08-26T16:47:18.824Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"7e003cd9-9886-4fb0-9209-95305cae9730"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for rakuten/rakutenai-7b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/rakuten-rakutenai-7b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Apache License, Version 2.0","url":"https://www.apache.org/licenses/LICENSE-2.0"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"How to make an authentic Spanish Omelette?","requestJson":"{\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"How to make an authentic Spanish Omelette?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Spanish Omelette is a simple dish made with potatoes, onions and eggs.\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"「馬が合う」はどう言う意味ですか","requestJson":"{\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"「馬が合う」はどう言う意味ですか\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"「馬が合う」とは、性格や考え方などが似ている、相性が良い、という意味です。\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"rakuten/rakutenai-7b-instruct"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","default":1024},"stream":{"type":"boolean","title":"Stream","description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","default":0.5},"top_p":{"type":"number","maximum":1,"minimum":0,"title":"Top P","description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","default":1},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","maximum":18446744073709552000,"minimum":0,"title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"type":"string"},{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far."}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"rakuten/rakutenai-7b-instruct"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2024-08-09T19:31:55.154Z","nvcfFunctionId":"760ad50f-7829-403d-a549-b1e97a44a9bb","createdDate":"2024-08-09T19:31:36.406Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/rakuten-rakutenai-7b-instruct","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License and Apache 2.0 License. \n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"rakutenai-7b-instruct"},"config":{"name":"rakutenai-7b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"rakutenai-7b-chat","displayName":"rakutenai-7b-chat","publisher":"rakuten","shortDescription":"Advanced state-of-the-art LLM with language understanding, superior reasoning, and text generation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/rakutenai-7b-chat.jpg","labels":["Chat","Language Generation","Large Language Models","Text-to-Text"],"attributes":[{"key":"AVAILABLE","value":"false"},{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-08-09T19:31:36.002Z","description":"$7f","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-08-26T16:47:18.747Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"50cd8515-7f45-432c-bff3-5ebe446c4f97"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for rakuten/rakutenai-7b-chat","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/rakuten-rakutenai-7b-chat for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Apache License, Version 2.0","url":"https://www.apache.org/licenses/LICENSE-2.0"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"How to make an authentic Spanish Omelette?","requestJson":"{\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"How to make an authentic Spanish Omelette?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"An authentic Spanish Omelette (Tortilla de Patatas) is a...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"「馬が合う」はどう言う意味ですか","requestJson":"{\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"「馬が合う」はどう言う意味ですか\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"「馬が合う」を端的に言うと、「気があう...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"rakuten/rakutenai-7b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"rakuten/rakutenai-7b-chat"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","default":1024},"stream":{"type":"boolean","title":"Stream","description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","default":0.5},"top_p":{"type":"number","maximum":1,"minimum":0,"title":"Top P","description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","default":1},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"seed":{"type":"integer","maximum":18446744073709552000,"minimum":0,"title":"Seed","description":"The model generates random results. Changing the input seed alone will produce a different response with similar characteristics. It is possible to reproduce results by fixing the input seed (assuming all other hyperparameters are also fixed).","default":0},"messages":{"anyOf":[{"type":"string"},{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far."}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"rakuten/rakutenai-7b-chat"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","nvcfFunctionId":"3cc0a374-0ab9-43f6-8283-ef1340306c4a","createdDate":"2024-08-09T19:31:36.321Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/rakuten-rakutenai-7b-chat","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License and Apache 2.0 License. \n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"rakutenai-7b-chat"},"config":{"name":"rakutenai-7b-chat","type":"model"}},{"endpoint":{"artifact":{"name":"phi-3-medium-128k-instruct","displayName":"phi-3-medium-128k-instruct","publisher":"microsoft","shortDescription":"Cutting-edge lightweight open language model exceling in high-quality reasoning.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/phi-3-medium-128k-instruct.jpg","labels":["Chat","Language Generation","Large Language Models","Text-to-Text","Code Generation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-01T21:43:42.006Z","description":"$80","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:00.095Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"0274e3a9-b859-419e-b956-e08d3b0d6ba9"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for microsoft/phi-3-medium-128k-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/microsoft-phi-3-medium-128k for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"MIT License","url":"https://opensource.org/license/MIT"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"tags":[{"name":"NVCF API","description":"Run inference on the model"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Write a limerick about the wonders of GPU computing.","requestJson":"{\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"There once was a GPU ...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"What can I see at NVIDIA's GPU Technology Conference?","requestJson":"{\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$NVIDIA_API_KEY\", \n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n)\n<% if (request.stream) { %>\nfor chunk in client.stream(<%- JSON.stringify(request.messages) %>): \n print(chunk.content, end=\"\")\n<% } else { %>\nresponse = client.invoke(<%- JSON.stringify(request.messages) %>)\nprint(response.content)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"microsoft/phi-3-medium-128k-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"microsoft/phi-3-medium-128k-instruct"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"seed":{"anyOf":[{"maximum":18446744073709552000,"minimum":0,"type":"integer"},{"type":"null"}],"default":null,"description":"If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.","examples":[42],"title":"Seed"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:55:00.726Z","nvcfFunctionId":"2975892e-2acd-49a5-8c4b-b76baf352bed","createdDate":"2024-07-01T21:43:42.694Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/microsoft-phi-3-medium-128k","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the MIT License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"projects":[{"name":"Build a Customizable Hybrid RAG Chatbot","url":"https://github.com/NVIDIA/workbench-example-hybrid-rag","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-workbench.jpg","workbench":true}],"playground":{"type":"chat"}},"artifactName":"phi-3-medium-128k-instruct"},"config":{"name":"phi-3-medium-128k-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"baichuan2-13b-chat","displayName":"baichuan2-13b-chat","publisher":"baichuan-inc","shortDescription":"Support Chinese and English chat, coding, math, instruction following, solving quizzes","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/baichuan2-13b-chat.jpg","labels":["Chat","Chinese Language Generation","Text-to-Text","Text Translation"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-24T20:29:38.892Z","description":"$81","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:55.804Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"2f51763b-10a5-450c-b59a-84eaf0e75e43"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for baichuan-inc/baichuan2-13b-chat","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/baichuan-inc-baichuan2-13b-chat for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Model license","url":"https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat/blob/main/Community%20License%20for%20Baichuan2%20Model.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"大熊猫爱吃什么？","requestJson":"{\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"大熊猫爱吃什么？\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"大熊猫主要吃竹子，特别是竹叶、竹芽和竹茎。此外，它们也会吃一些草本植物、水果和小型哺乳动物。大熊猫是中国的国宝，生活在四川、陕西和甘肃等地的山区。\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Generate a C++ program to implement the quicksort algorithm.","requestJson":"{\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Generate a C++ program to implement the quicksort algorithm.\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Here's a C++ function implementing the quicksort algorithm...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"baichuan-inc/baichuan2-13b-chat\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"baichuan-inc/baichuan2-13b-chat"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","default":1024},"stream":{"type":"boolean","title":"Stream","description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","default":0.5},"top_p":{"type":"number","maximum":1,"minimum":0,"title":"Top P","description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","default":1},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"messages":{"anyOf":[{"type":"string"},{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far.","maxItems":1}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"baichuan-inc/baichuan2-13b-chat"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-01-17T20:16:56.409Z","nvcfFunctionId":"e34accba-5d27-4960-84e2-e4f9f8777e4f","createdDate":"2024-07-24T20:29:39.157Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/baichuan-inc-baichuan2-13b-chat","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use. The use of this model is governed by Apache 2.0 and the Community License for Baichuan2 Model.\n","showUnavailableBanner":false,"cta":{"type":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"baichuan2-13b-chat"},"config":{"name":"baichuan2-13b-chat","type":"model"}},{"endpoint":{"artifact":{"name":"chatglm3-6b","displayName":"chatglm3-6b","publisher":"thudm","shortDescription":"Supports Chinese and English languages to handle tasks including chatbot, content generation, coding, and translation.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/chatglm3-6b.jpg","labels":["Chat","Regional Language Generation","Text-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-07-24T20:33:22.113Z","description":"$82","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-08-26T16:46:34.191Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"da757c2b-713d-4b89-ad40-8c4097c521eb"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for thudm/chatglm3-6b","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/thudm-chatglm3-6b for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Model license","url":"https://huggingface.co/THUDM/chatglm3-6b/blob/main/MODEL_LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletionResponse"}}}},"402":{"description":"Payment Required","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaymentRequiredError"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"大熊猫爱吃什么？","requestJson":"{\n \"model\": \"thudm/chatglm3-6b\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"大熊猫爱吃什么？\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"thudm/chatglm3-6b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"大熊猫主要吃竹子，特别是竹叶、竹芽和竹茎。此外，它们也会吃一些草本植物、水果和小型哺乳动物。大熊猫是中国的国宝，生活在四川、陕西和甘肃等地的山区。\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"Hi, describe the city you live in","requestJson":"{\n \"model\": \"thudm/chatglm3-6b\",\n \"messages\": [\n {\n \"role\": \"system\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hi, describe the city you live in\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"stop\": null,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"thudm/chatglm3-6b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Hi, I am ChatGLM3-6B, an AI assistant based on a language model.\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"thudm/chatglm3-6b\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"thudm/chatglm3-6b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"ChatCompletionRequest":{"properties":{"model":{"type":"string","title":"Model","default":"thudm/chatglm3-6b"},"max_tokens":{"type":"integer","minimum":1,"title":"Max Tokens","description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","default":1024},"stream":{"type":"boolean","title":"Stream","description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","default":false},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","default":0.5},"top_p":{"type":"number","maximum":1,"minimum":0,"title":"Top P","description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","default":1},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence.","examples":[null]},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"messages":{"anyOf":[{"type":"string"},{"items":{"additionalProperties":{"type":"string"},"type":"object"},"type":"array"}],"title":"Messages","description":"A list of messages comprising the conversation so far.","maxItems":1}},"additionalProperties":false,"type":"object","required":["messages"],"title":"ChatCompletionRequest","description":"OpenAI ChatCompletionRequest"},"ChatCompletionResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the completion."},"object":{"type":"string","title":"Object","default":"chat.completion"},"created":{"type":"integer","title":"Created"},"model":{"type":"string","title":"Model","example":"thudm/chatglm3-6b"},"choices":{"items":{"$ref":"#/components/schemas/ChatCompletionResponseChoice"},"type":"array","title":"Choices","description":"The list of completion choices the model generated for the input prompt."},"usage":{"$ref":"#/components/schemas/UsageInfo","description":"Usage statistics for the completion request."}},"type":"object","required":["model","choices","usage"],"title":"ChatCompletionResponse"},"ChatCompletionResponseChoice":{"properties":{"index":{"type":"integer","title":"Index","description":"The index of the choice in the list of choices (always 0)."},"message":{"$ref":"#/components/schemas/ChatMessage","description":"A chat completion message generated by the model."},"finish_reason":{"anyOf":[{"type":"string","enum":["stop","length"]},{"type":"null"}],"title":"Finish Reason","description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished"}},"type":"object","required":["index","message"],"title":"ChatCompletionResponseChoice"},"ChatMessage":{"properties":{"role":{"type":"string","title":"Role","description":"The role of the message author."},"content":{"type":"string","title":"Content","description":"The contents of the message."}},"type":"object","required":["role","content"],"title":"ChatMessage"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail","description":"Detailed information about the error."}},"type":"object","title":"HTTPValidationError"},"PaymentRequiredError":{"properties":{"detail":{"type":"string","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"},"UsageInfo":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","description":"Number of tokens in the prompt.","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","description":"Total number of tokens used in the request (prompt + completion).","default":0},"completion_tokens":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Completion Tokens","description":"Number of tokens in the generated completion.","default":0}},"type":"object","title":"UsageInfo"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message","description":"The error message."},"type":{"type":"string","title":"Error Type","description":"Error type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2024-08-14T16:39:04.894Z","nvcfFunctionId":"14a5cd57-c018-47fe-bcad-8ef24329e512","createdDate":"2024-07-24T20:33:22.447Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/thudm-chatglm3-6b","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use. The use of this model is governed by the Beijing Zhipu Huazhang Technology Co., Ltd. Commercial Use License Agreement.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"chatglm3-6b"},"config":{"name":"chatglm3-6b","type":"model"}},{"endpoint":null,"spec":null,"config":{"name":"codestral-22b-instruct-v01","type":"model"}},{"endpoint":{"artifact":{"name":"palmyra-med-70b","displayName":"palmyra-med-70b","publisher":"writer","shortDescription":"Leading LLM for accurate, contextually relevant responses in the medical domain.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/palmyra-med-70b.jpg","labels":["Healthcare","Text-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-06-11T01:40:38.556Z","description":"$83","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:17.009Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"6b6662d3-8b63-434f-8122-10c3124f8c1e"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for writer/palmyra-med-70b","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/writer-palmyra-med-70b for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Writer License","url":"https://writer.com/legal/open-model-license/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Does danzhi Xiaoyao San ameliorate depressive-like behavior by shifting toward serotonin via the downregulation of hippocampal indoleamine 2,3-dioxygenase?","requestJson":"{\n \"model\": \"writer/palmyra-med-70b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Does danzhi Xiaoyao San ameliorate depressive-like behavior by shifting toward serotonin via the downregulation of hippocampal indoleamine 2,3-dioxygenase?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"How long does it take for newborn jaundice to go away?","requestJson":"{\n \"model\": \"writer/palmyra-med-70b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How long does it take for newborn jaundice to go away?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"writer/palmyra-med-70b\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"writer/palmyra-med-70b"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:17.837Z","nvcfFunctionId":"aab71274-5281-4941-b0b8-20f339d1fc7e","createdDate":"2024-06-11T01:40:38.914Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/writer-palmyra-med-70b","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Service Agreement; and the use of this model is governed by the Writer Open Model License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"palmyra-med-70b"},"config":{"name":"palmyra-med-70b","type":"model"}},{"endpoint":{"artifact":{"name":"palmyra-med-70b-32k","displayName":"palmyra-med-70b-32k","publisher":"writer","shortDescription":"Leading LLM for accurate, contextually relevant responses in the medical domain.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/palmyra-med-70b-32k.jpg","labels":["Healthcare","Text-to-Text"],"attributes":[{"key":"PREVIEW","value":"true"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-06-11T01:40:41.104Z","description":"$84","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:14.698Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"f2343033-5ca4-4c18-85b0-0dd80e88d62c"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for writer/palmyra-med-70b-32k","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/writer-palmyra-med-70b-32k for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Writer License","url":"https://writer.com/legal/open-model-license/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatRequest"}}},"required":true},"responses":{"200":{"description":"Invocation is fulfilled","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ChatCompletion"}},"text/event-stream":{"schema":{"$ref":"#/components/schemas/ChatCompletionChunk"}}}},"202":{"description":"Result is pending. Client should poll using the requestId.\n","content":{"application/json":{"example":{},"schema":{}}},"headers":{"NVCF-REQID":{"description":"requestId required for pooling","schema":{"type":"string","format":"uuid"}},"NVCF-STATUS":{"description":"Invocation status","schema":{"type":"string"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:unprocessable-entity","title":"Unprocessable Entity","status":422,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/4a58c6cb-a9b4-4014-99de-3e704d4ae687","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}},"x-nvai-meta":{"name":"Create chat completion","returns":"Returns a [chat completion](/docs/api-reference/chat/object) object, or a streamed sequence of [chat completion chunk](/docs/api-reference/chat/streaming) objects if the request is streamed.\n","path":"create","examples":[{"name":"Does danzhi Xiaoyao San ameliorate depressive-like behavior by shifting toward serotonin via the downregulation of hippocampal indoleamine 2,3-dioxygenase?","requestJson":"{\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Does danzhi Xiaoyao San ameliorate depressive-like behavior by shifting toward serotonin via the downregulation of hippocampal indoleamine 2,3-dioxygenase?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The python functions...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"},{"name":"How long does it take for newborn jaundice to go away?","requestJson":"{\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How long does it take for newborn jaundice to go away?\"\n }\n ],\n \"top_p\": 0.7,\n \"max_tokens\": 1024,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$NVIDIA_API_KEY\"\n)\n\ncompletion = client.chat.completions.create(\n model=\"<%- request.model %>\",\n messages=<%- JSON.stringify(request.messages) %>,\n temperature=<%- request.temperature %>,\n top_p=<%- request.top_p %>,\n max_tokens=<%- request.max_tokens %>,\n stream=<%- request.stream?.toString()[0].toUpperCase() + request.stream?.toString().slice(1) %>\n)\n<% if (request.stream) { %>\nfor chunk in completion:\n if chunk.choices[0].delta.content is not None:\n print(chunk.choices[0].delta.content, end=\"\")\n<% } else { %>\nprint(completion.choices[0].message)\n<% } %>\n","node.js":"import OpenAI from 'openai';\n\nconst openai = new OpenAI({\n apiKey: '$NVIDIA_API_KEY',\n baseURL: 'https://integrate.api.nvidia.com/v1',\n})\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"<%- request.model %>\",\n messages: <%- JSON.stringify(request.messages) %>,\n temperature: <%- request.temperature %>,\n top_p: <%- request.top_p %>,\n max_tokens: <%- request.max_tokens %>,\n stream: <%- request.stream %>,\n })\n <% if (request.stream) { %>\n for await (const chunk of completion) {\n process.stdout.write(chunk.choices[0]?.delta?.content || '')\n }\n <% } else { %>\n process.stdout.write(completion.choices[0]?.message?.content);\n <% } %>\n}\n\nmain();","curl":"curl https://integrate.api.nvidia.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"messages\": <%- JSON.stringify(request.messages).replaceAll(\"'\", \"'\\\"'\\\"'\") %>,\n \"temperature\": <%- request.temperature %>, \n \"top_p\": <%- request.top_p %>,\n \"max_tokens\": <%- request.max_tokens %>,\n \"stream\": <%- request.stream %> \n }'\n"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"writer/palmyra-med-70b-32k\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/Choice"},"title":"Choices","type":"array"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the completion request."}},"required":["id","choices","usage"],"title":"ChatCompletion","type":"object"},"ChatCompletionChunk":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$ref":"#/components/schemas/ChoiceChunk"},"title":"Choices","type":"array"}},"required":["id","choices"],"title":"ChatCompletionChunk","type":"object"},"ChatRequest":{"additionalProperties":false,"properties":{"model":{"type":"string","title":"Model","default":"writer/palmyra-med-70b-32k"},"messages":{"description":"A list of messages comprising the conversation so far. The roles of the messages must be alternating between `user` and `assistant`. The last input message should have role `user`. A message with the the `system` role is optional, and must be the very first message if it is present; `context` is also optional, but must come before a user question.","examples":[[{"content":"I am going to Paris, what should I see?","role":"user"}]],"items":{"$ref":"#/components/schemas/Message"},"title":"Messages","type":"array"},"temperature":{"default":0.2,"description":"The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"minimum":0,"title":"Temperature","type":"number"},"top_p":{"default":0.7,"description":"The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not recommended to modify both temperature and top_p in the same call.","maximum":1,"exclusiveMinimum":0,"title":"Top P","type":"number"},"frequency_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Frequency Penalty","description":"Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim."},"presence_penalty":{"type":"number","maximum":2,"minimum":-2,"default":0,"title":"Presence Penalty","description":"Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics."},"max_tokens":{"default":1024,"description":"The maximum number of tokens to generate in any given call. Note that the model is not aware of this value, and generation will simply stop at the number of tokens specified.","maximum":4096,"minimum":1,"title":"Max Tokens","type":"integer"},"stream":{"default":false,"description":"If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events (SSE) as they become available (JSON responses are prefixed by `data: `), with the stream terminated by a `data: [DONE]` message.","title":"Stream","type":"boolean"},"stop":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Stop","description":"A string or a list of strings where the API will stop generating further tokens. The returned text will not contain the stop sequence."},"bad":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"string"},{"type":"null"}],"title":"Bad","description":"A word or list of words not to use. The words are case sensistive."}},"required":["messages"],"title":"ChatRequest","type":"object"},"Choice":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"message":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion message generated by the model.","examples":[{"content":"Ah, Paris, the City of Light! There are so many amazing things to see and do in this beautiful city ...","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached.","examples":["stop"],"title":"Finish Reason"}},"required":["index","message"],"title":"Choice","type":"object"},"ChoiceChunk":{"properties":{"index":{"description":"The index of the choice in the list of choices (always 0).","title":"Index","type":"integer"},"delta":{"allOf":[{"$ref":"#/components/schemas/Message"}],"description":"A chat completion delta generated by streamed model responses.","examples":[{"content":"Ah,","role":"assistant"}]},"finish_reason":{"anyOf":[{"enum":["stop","length"],"type":"string"},{"type":"null"}],"default":null,"description":"The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, or `length` if the maximum number of tokens specified in the request was reached. Will be `null` if the model has not finished generating.","title":"Finish Reason"}},"required":["index","delta"],"title":"ChoiceChunk","type":"object"},"Message":{"additionalProperties":false,"properties":{"role":{"description":"The role of the message author.","enum":["system","context","user","assistant"],"title":"Role","type":"string"},"content":{"description":"The contents of the message.","title":"Content","type":"string"}},"required":["role","content"],"title":"Message","type":"object"},"Usage":{"properties":{"completion_tokens":{"description":"Number of tokens in the generated completion.","examples":[25],"title":"Completion Tokens","type":"integer"},"prompt_tokens":{"description":"Number of tokens in the prompt.","examples":[9],"title":"Prompt Tokens","type":"integer"},"total_tokens":{"description":"Total number of tokens used in the request (prompt + completion).","examples":[34],"title":"Total Tokens","type":"integer"}},"required":["completion_tokens","prompt_tokens","total_tokens"],"title":"Usage","type":"object"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2024-11-18T22:31:15.533Z","nvcfFunctionId":"d6faa974-3591-49a4-963d-97221d074b2e","createdDate":"2024-06-11T01:40:41.493Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/writer-palmyra-med-70b-32k","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Service Agreement; and the use of this model is governed by the Writer Open Model License.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"playground":{"type":"chat"}},"artifactName":"palmyra-med-70b-32k"},"config":{"name":"palmyra-med-70b-32k","type":"model"}}],"items":["$85","$86","$87","$88","$89","$8a","$8b","$8c","$8d","$8e","$8f","$90","$91","$92","$93","$94","$95","$96","$97","$98","$99","$9a","$9b","$9c","$9d","$9e","$9f","$a0","$a1"],"params":{"category":"reasoning"},"slotTitle":[["$","div",null,{"className":"mb-2 flex items-start gap-2 max-xs:justify-between","children":[["$","h2",null,{"className":"text-ml font-medium leading-body tracking-less text-manitoulinLightWhite mb-0","children":"Fresh Off the Press"}],"$undefined"]}],["$","p",null,{"className":"text-md font-normal text-manitoulinLightGray mb-0","children":"The latest innovations in intelligence models"}]," "]}]