39:["$","$L3d",null,{"data":[{"endpoint":{"artifact":{"name":"deepseek-r1-distill-llama-8b","displayName":"deepseek-r1-distill-llama-8b","publisher":"deepseek-ai","shortDescription":"Distilled version of Llama 3.1 8B using reasoning data generated by DeepSeek R1 for enhanced performance.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/deepseek-r1-distill-llama-8b.jpg","labels":["Distillation","coding","math","reasoning","run on rtx"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-03-17T17:48:42.953Z","description":"$7c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-17T23:23:36.839Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"24092b6b-7da8-49bc-acb0-69bd2f73b691"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for deepseek-ai/deepseek-r1-distill-llama-8b","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-r1-distill-llama-8b for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"MIT License","url":"https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B/blob/main/LICENSE"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$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":"Which number is larger, 9.11 or 9.8?","requestJson":"{\n \"model\": \"deepseek-ai/deepseek-r1-distill-llama-8b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Which number is larger, 9.11 or 9.8?\"\n }\n ],\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1-distill-llama-8b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The number 9.11 is...\"\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 many 'r's are in the word 'strawberry'?","requestJson":"{\n \"model\": \"deepseek-ai/deepseek-r1-distill-llama-8b\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"How many 'r's are in the word 'strawberry'?\"\n }\n ],\n \"max_tokens\": 4096,\n \"seed\": 42,\n \"stream\": true\n}\n","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1-distill-llama-8b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"In the word strawberry, there are...\"\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":"$7d","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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":"$7e","curl":"$7f"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"deepseek-ai/deepseek-r1-distill-llama-8b\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$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":"deepseek-ai/deepseek-r1-distill-llama-8b"},"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":0.6,"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":4096,"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":["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":"2025-04-17T23:23:37.273Z","nvcfFunctionId":"daa3e658-bf63-49bb-ac12-5c37edb8879f","createdDate":"2025-03-17T17:48:43.209Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/deepseek-ai-deepseek-r1-distill-llama-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 NVIDIA Community Model License. ADDITIONAL INFORMATION: MIT License; 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/deepseek-ai/containers/deepseek-r1-distill-llama-8b"},"playground":{"type":"chatWithThinking"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$80"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$81"}]},"artifactName":"deepseek-r1-distill-llama-8b"},"config":{"name":"deepseek-r1-distill-llama-8b","type":"model"}},{"endpoint":{"artifact":{"name":"flux_1-dev","displayName":"FLUX.1-dev","publisher":"black-forest-labs","shortDescription":"FLUX.1 is a state-of-the-art suite of image generation models","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/flux_1-dev.jpg","labels":["Run on RTX","Image Generation","Text-to-Image"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2025-04-09T22:58:24.102Z","description":"$82","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-17T01:55:23.578Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"45fe969e-1363-4be3-8e5c-56c9013b2c49"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim for more details.","license":{"name":"Stability AI CreativeML Open RAIL++-M","url":"https://github.com/Stability-AI/generative-models/blob/main/model_licenses/LICENSE-SDXL1.0"},"termsOfService":"https://nvidia.com/legal/terms-of-use","title":"NVIDIA NIM API for black-forest-labs/flux.1-dev","version":"1.0.0"},"servers":[{"url":"https://ai.api.nvidia.com/v1/"}],"paths":{"/genai/stabilityai/sdxl":{"post":{"operationId":"_infer_infer_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ImageRequest"}}},"required":true},"responses":{"200":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ImageResponse"}}},"description":"Successful Response"},"422":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}},"description":"Validation Error"}},"summary":" Infer","x-nvai-meta":{"examples":[{"name":"Example 1 base","input":{"text":"a simple coffee shop interior"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 base","input":{"text":"a coffee shop patio"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/2.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 base","input":{"text":"a surreal dreamscape with waterfalls cascading, and a giant glowing moon in the background. Ethereal lighting"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 4 base","input":{"text":"photographic shot of Ancient pyramid shaped temple ruins in the foreground"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/base/output/4.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"base\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 1 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"a bottle of lemonade on a round platter with lemons, limes, sugar bowl"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"a bottle of olive oil on a table with cherry tomatoes, parmesan cheese, garlic and onions"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/2.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 canny","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","text":"an artistic drawing in charcoal pencil of a wine bottle with cheese and fruit, dark strokes"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"canny\", \"image\": \"data:image/png;example_id,0\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 1 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/1.jpg","text":"A simple coffee shop interior"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/1.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,1\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 2 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/3.jpg","text":"A surreal dreamscape with floating islands, waterfalls cascading into the sky, and a giant glowing moon in the background. Ethereal lighting, highly detailed, 8K resolution"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/3.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,2\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"},{"name":"Example 3 depth","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/4.jpg","text":"The ruins of an ancient temple lie at the bottom of the ocean, exotic fish swim nearby sea life and coral are everywhere"},"output":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/output/4.jpg"},"requestJson":"{ \"text_prompts\": [ { \"text\": \"<%- input.text %>\", \"weight\": 1 } ], \"mode\": \"depth\", \"image\": \"data:image/png;example_id,3\", \"steps\": 50, \"cfg_scale\": 3.5, \"seed\": 0 }"}],"name":"Generate a new image from a text prompt","path":"infer","returns":"Returns an Image artifact that consists from a generated image (JPEG) encoded in base64, finish reason and a seed used during the generation","templates":[{"requestEjs":{"curl":"$83","node.js":"$84","python":"$85"},"response":"{\n \"artifacts\": [\n {\n \"base64\": \"...very long string...\",\n \"finishReason\": \"SUCCESS\",\n \"seed\": 1100106574\n }\n ]\n}\n","title":"Example"}]}}}},"components":{"schemas":{"Artifact":{"properties":{"base64":{"description":"A base64-encoded string of the generated image (JPEG)","examples":["/9j/4AAQSkZ...b+AVZ/9k="],"title":"Base64","type":"string"},"finishReason":{"allOf":[{"$ref":"#/components/schemas/FinishReason"}],"description":"The result of the generation process. `SUCCESS` indicates success. `ERROR` indicates an error. `CONTENT_FILTERED` indicates the result affected by the content filter"},"seed":{"description":"The seed used during generation","title":"Seed","type":"integer"}},"required":["base64","finishReason","seed"],"title":"Artifact","type":"object"},"FinishReason":{"enum":["CONTENT_FILTERED","ERROR","SUCCESS"],"title":"FinishReason","type":"string"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"title":"Detail","type":"array"}},"title":"HTTPValidationError","type":"object"},"ImageRequest":{"additionalProperties":false,"properties":{"height":{"default":1024,"description":"Height of the image to generate, in pixels. Only height=1024 is supported","enum":[768,832,896,960,1024,1088,1152,1216,1280,1344],"title":"Height","type":"integer"},"width":{"default":1024,"description":"Width of the image to generate, in pixels. Only width=1024 is supported","enum":[768,832,896,960,1024,1088,1152,1216,1280,1344],"title":"Width","type":"integer"},"text_prompts":{"description":"An array of text prompts to use for generation","items":{"$ref":"#/components/schemas/TextPrompt"},"maxItems":1,"minItems":1,"title":"Text Prompts","type":"array"},"cfg_scale":{"default":5,"description":"How strictly the diffusion process adheres to the prompt text (higher values keep your image closer to your prompt).","exclusiveMinimum":1,"maximum":9,"title":"Cfg Scale","type":"number"},"mode":{"enum":["base","canny","depth"],"type":"string","default":"base","description":"NIM inference mode. If canny or depth is selected an image input is required","title":"Mode"},"image":{"type":"string","description":"An image input with a depth map or canny edges used if the mode is depth or canny respectively. The image should be in form of `data:image/{format};base64,{base64encodedimage}` if it's smaller than 200KB. Otherwise, it needs to be uploaded to a presigned S3 bucket using NVCF Asset APIs.Once uploaded you can refer to it using the following format: `data:image/png;asset_id,{asset_id}`.Accepted formats are `jpg`, `png` and `jpeg`.","examples":["data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAAEElEQVR4nGK6HcwNCAAA//8DTgE8HuxwEQAAAABJRU5ErkJggg==","data:image/png;asset_id,5576911c-6031-47a4-8796-bb506b026ad0"],"title":"Image"},"samples":{"default":1,"description":"Number of images to generate. Only samples=1 is supported","maximum":1,"minimum":1,"title":"Samples","type":"integer"},"seed":{"default":0,"description":"The seed which governs generation. Changing the seed with other inputs fixed results in different outputs. (Use 0 for a random seed)","exclusiveMaximum":4294967296,"minimum":0,"title":"Seed","type":"integer"},"steps":{"default":50,"description":"The number of diffusion steps applied to generate an output image.","maximum":100,"minimum":5,"title":"Steps","type":"integer"}},"required":["text_prompts"],"title":"ImageRequest","type":"object"},"ImageResponse":{"properties":{"artifacts":{"items":{"$ref":"#/components/schemas/Artifact"},"maxItems":1,"minItems":1,"title":"Artifacts","type":"array"}},"required":["artifacts"],"title":"ImageResponse","type":"object"},"TextPrompt":{"additionalProperties":false,"properties":{"text":{"description":"The prompt itself","examples":["A photo of a Shiba Inu dog with a backpack riding a bike"],"title":"Text","type":"string"},"weight":{"default":1,"description":"Weight of the prompt, only weight=1.0 for prompt and weight=-1 for negative prompt is supported","enum":[1],"title":"Weight","type":"number"}},"required":["text"],"title":"TextPrompt","type":"object"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"title":"Location","type":"array"},"msg":{"title":"Message","type":"string"},"type":{"title":"Error Type","type":"string"}},"required":["loc","msg","type"],"title":"ValidationError","type":"object"}},"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}}},"security":[{"Token":[]}]},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-17T01:55:24.213Z","nvcfFunctionId":"0c474133-6fd2-42f6-be29-8ebbbaeaaeb2","createdDate":"2025-04-09T22:58:24.415Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/black-forest-labs-flux_1-dev","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Contact sales@blackforestlabs.ai for commercial terms to use the Flux.1-dev model. ADDITIONAL INFORMATION: Apache 2.0, NVIDIA Community Model License Agreement and Llama 2 Community Model License Agreement.\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/black-forest-labs/containers/flux.1-dev"},"maxRequests":25,"playground":{"type":"custom","input":{"items":[{"key":"mode","type":"select"},{"key":"prompt","type":"text-area","placeholder":"A photorealistic painting of a majestic mountain range in the morning light, with a river winding through the valley below. The mountains are covered in lush green forests and snow-capped peaks, and the river is clear and sparkling.","title":"Prompt","description":"Enter a prompt to receive an AI-generated image."},{"key":"image","type":"image-select","optional":true,"visible":"<%- request.mode && request.mode !== \"base\" %>","images":["https://assets.ngc.nvidia.com/products/api-catalog/flux/canny/input/1.jpg","https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/1.jpg","https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/3.jpg","https://assets.ngc.nvidia.com/products/api-catalog/flux/depth/input/4.jpg"],"mode":"index","title":"Input Image"}]},"parameters":{"items":[{"key":"ratio","type":"radio","title":"Ratio","description":"Output Image Ratio","values":["1:1","16:9","9:16","5:4","4:5","3:2","2:3"],"defaultValue":"1:1"}],"omitProperties":["mode","samples","height","width"]},"output":{"flags":"{ \"isNSFW\": { \"condition\": <%- response.artifacts[0].finishReason === \"CONTENT_FILTERED\" %>, \"type\": \"ValidationError\", \"description\": \"provided input produces NSFW content\" } }","items":[{"key":"artifacts[0].base64","type":"image","base64Format":"data:image/jpeg;base64,"}]},"requestBody":"{ \"text_prompts\": [ { \"text\": <%- JSON.stringify(request.prompt) %>, \"weight\": 1 } ], <% switch(request.ratio) { case \"16:9\": %> \"width\": 768, \"height\": 1344, <% break; case \"9:16\": %> \"width\": 1344, \"height\": 768, <% break; case \"5:4\": %> \"width\": 896, \"height\": 1152, <% break; case \"4:5\": %> \"width\": 1152, \"height\": 896, <% break; case \"3:2\": %> \"width\": 832, \"height\": 1216, <% break; case \"2:3\": %> \"width\": 1216, \"height\": 832, <% break; case \"1:1\": default: %> \"width\": 1024, \"height\": 1024, <% break; } %> \"mode\": <%- JSON.stringify(request.mode) %>, <% if (request.mode !== \"base\") { %> \"image\": \"<%- request.image %>\", <% } %> \"steps\": <%- request.steps %>, \"cfg_scale\": <%- request.cfg_scale %>, \"seed\": <%- request.seed %> }"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$86"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$87"}]},"artifactName":"flux_1-dev"},"config":{"name":"flux_1-dev","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":"$88","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-25T15:11:46.427Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"8005b0e9-ef06-43c5-ad6f-8aa528eb97f8"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nv-mistralai/mistral-nemo-12b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nv-mistralai-mistral-nemo-12b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Apache 2.0","url":"https://mistral.ai/terms-of-service/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$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":"$89","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":"$8a","responseJson":"{\n \"id\": \"id-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"nv-mistralai/mistral-nemo-12b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"At NVIDIA's GPU Technology Conference (GTC)...\"\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}],"templates":[{"title":"No Streaming","requestEjs":{"python":"from openai import OpenAI\n\nclient = OpenAI(\n base_url = \"https://integrate.api.nvidia.com/v1\",\n api_key = \"$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":"$8b"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$8c"}]},"artifactName":"mistral-nemo-12b-instruct"},"config":{"name":"mistral-nemo-12b-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":"$8d","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-04-17T23:20:56.851Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"95082e1d-8ada-43ef-8c64-4a5911c791a5"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for meta/llama-3.1-8b-instruct","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/meta-llama-3_1-8b-instruct for more details.","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/","contact":{"name":"NVIDIA Enterprise Support","url":"https://www.nvidia.com/en-us/support/enterprise/"},"license":{"name":"Llama 3.1 License","url":"https://github.com/meta-llama/llama-models/blob/main/License/Llama3.1.txt"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1/"}],"paths":{"/chat/completions":{"post":{"operationId":"create_chat_completion_v1_chat_completions_post","tags":["Chat"],"summary":"Creates a model response for the given chat conversation.","description":"Given a list of messages comprising a conversation, the model will return a response. Compatible with OpenAI. See https://platform.openai.com/docs/api-reference/chat/create","requestBody":{"content":{"application/json":{"schema":{"$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":"$8e","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":"$8f","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":"$90","langChain":"from langchain_nvidia_ai_endpoints import ChatNVIDIA\n\nclient = ChatNVIDIA(\n model=\"<%- request.model %>\",\n api_key=\"$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":"$91","curl":"$92"},"response":"{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1677652288,\n \"model\": \"meta/llama-3.1-8b-instruct\",\n \"system_fingerprint\": \"fp_44709d6fcb\",\n \"choices\": [{\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"\\n\\nHello there, how may I assist you today?\",\n },\n \"finish_reason\": \"stop\"\n }],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 12,\n \"total_tokens\": 21\n }\n}\n"}]}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"Errors":{"properties":{"type":{"type":"string","description":"Error type"},"title":{"type":"string","description":"Error title"},"status":{"type":"integer","description":"Error status code"},"detail":{"type":"string","description":"Detailed information about the error"},"instance":{"type":"string","description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"},"ChatCompletion":{"properties":{"id":{"description":"A unique identifier for the completion.","format":"uuid","title":"Id","type":"string"},"choices":{"description":"The list of completion choices the model generated for the input prompt.","items":{"$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":"$93"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$94"}]},"artifactName":"llama-3_1-8b-instruct"},"config":{"name":"llama-3_1-8b-instruct","type":"model"}},{"endpoint":{"artifact":{"name":"parakeet-ctc-0_6b-asr","displayName":"parakeet-ctc-0.6b-asr","publisher":"nvidia","shortDescription":"State-of-the-art accuracy and speed for English transcriptions.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/parakeet-ctc-0_6b-asr.jpg","labels":["ASR","Batch","English","Fast","NVIDIA NIM","Run on RTX","Streaming","Speech-to-Text"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","bias":"Field | Response\n:---------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------\nWhat is the language balance of the model validation data? | English: 100%\nWhat is the geographic origin language balance of the model validation data? | United States: 80%, United Kingdom: 10%, Others: 10%\nWhat is the accent balance of the model validation data? | American English: 80%, British English: 10%, Others: 10%\nParticipation considerations from adversely impacted groups ([protected classes](https://www.senate.ca.gov/content/protected-classes)) in model design and testing: | Age, Gender, Linguistic Background\nMeasures taken to mitigate against unwanted bias: | Used custom dataset to validate model performance across gender, age, and linguistic demographics","canGuestDownload":true,"createdDate":"2024-08-06T06:27:13.040Z","description":"$95","explainability":"$96","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$97","safetyAndSecurity":"Field | Response\n:---------------------------------------------------|:----------------------------------\nModel Application(s): | Speech Transcription\nDescribe the life-critical impacts (if present). | Not Applicable\nUse Case Restriction(s): | Abide by https://developer.nvidia.com/riva/ga/license\nDescribe access restrictions (if any): | The Principle of Least Privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training and dataset license constraints adhered to.","updatedDate":"2025-03-24T23:59:02.186Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"dbf6a7e6-e2bf-4ccf-a33c-0e451f2e13b3"}},"spec":{"namespace":"qc69jvmznzxy","updatedDate":"2025-03-24T23:59:03.026Z","nvcfFunctionId":"d8dd4e9b-fbf5-4fb0-9dba-8cf436c8d965","createdDate":"2024-08-06T06:27:13.383Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/riva/asr/latest/protos.html","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.\n","showUnavailableBanner":false,"cta":{"text":"Run Anywhere - Notify Me","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/","nim_available_override_url":"https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/parakeet-0-6b-ctc-en-us"},"usage":"$98","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$99"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$9a"}]},"artifactName":"parakeet-ctc-0_6b-asr"},"config":{"name":"parakeet-ctc-0_6b-asr","type":"model"}},{"endpoint":{"artifact":{"name":"studiovoice","displayName":"studiovoice","publisher":"nvidia","shortDescription":"Enhance speech by correcting common audio degradations to create studio quality speech output.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/studiovoice.jpg","labels":["Digital Human","Nvidia Maxine","Run on RTX","Speech Enhancement","Speech-to-speech"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","bias":"| Field | Response |\n|-------|----------|\n| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | Age (18+), Gender |\n| Measures taken to mitigate against unwanted bias: | Evaluated using internal, proprietary data mix to achieve similar key performance indicators. |","canGuestDownload":true,"createdDate":"2024-10-03T00:40:13.315Z","description":"$9b","explainability":"$9c","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$9d","safetyAndSecurity":"| Field | Response |\n|-------|----------|\n| Model Application(s): | Speech Enhancement |\n| Describe the life critical impact (if present). | Not Applicable for licensed use cases per [Maxine Evaluation EULA](https://developer.download.nvidia.com/maxine/nvidia-maxine-evaluation-license-24oct2023.pdf) |\n| Use Case Restrictions: | Abide by [Maxine Evaluation EULA](https://developer.download.nvidia.com/maxine/nvidia-maxine-evaluation-license-24oct2023.pdf) |\n| Model and dataset restrictions: | The Principle of Least Privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |","updatedDate":"2025-04-10T16:03:13.392Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"1034b1b9-a4aa-4d8b-a822-e73f3ee73023"}},"spec":{"namespace":"qc69jvmznzxy","updatedDate":"2025-04-10T16:03:13.849Z","nvcfFunctionId":"3f0aeba3-6d91-4465-b8cc-cc2aef355186","createdDate":"2024-10-03T00:40:13.518Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/maxine/studio-voice/latest/index.html","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.\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/nvidia/containers/maxine-studio-voice"},"usage":"$9e","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$9f"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$a0"}]},"artifactName":"studiovoice"},"config":{"name":"studiovoice","type":"model"}},{"endpoint":{"artifact":{"name":"llama-3_2-nv-embedqa-1b-v2","displayName":"llama-3.2-nv-embedqa-1b-v2","publisher":"nvidia","shortDescription":"Multilingual and cross-lingual text question-answering retrieval with long context support and optimized data storage efficiency.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/llama-3_2-nv-embedqa-1b-v2.jpg","labels":["embedding","nemo retriever","run on rtx","Retrieval Augmented Generation","Text-to-Embedding"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","bias":"| Field | Response |\n| ----- | ----- |\n| Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing | None |\n| Measures taken to mitigate against unwanted bias | None |","canGuestDownload":true,"createdDate":"2024-12-16T21:01:03.160Z","description":"$a1","explainability":"$a2","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$a3","safetyAndSecurity":"| Field | Response |\n| ----- | ----- |\n| Model Application(s): | Text Embedding for Retrieval |\n| Describe the physical safety impact (if present). | Not Applicable |\n| Use Case Restrictions: | Abide by [NVIDIA AI Foundation Models Community License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). |\n| Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to. |","updatedDate":"2025-03-24T23:53:37.185Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"4e260848-72b2-4e2c-86e2-5053451b6c7f"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/llama-3.2-nv-embedqa-1b-v2","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_2-nv-embedqa-1b-v2 for more details.","version":"1.0.0","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"paths":{"/embeddings":{"post":{"tags":["Embeddings"],"summary":"Creates an embedding vector from the input text.","operationId":"create_embedding","requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","properties":{"input":{"description":"Input text to embed. Max length is 8192 tokens.","oneOf":[{"type":"string"},{"items":{"type":"string"},"type":"array"}],"minLength":1,"maxLength":8192,"title":"Input"},"model":{"type":"string","description":"ID of the embedding model.","example":"nvidia/llama-3.2-nv-embedqa-1b-v2","default":"nvidia/llama-3.2-nv-embedqa-1b-v2","title":"Model"},"input_type":{"type":"string","enum":["passage","query"],"description":"nvidia/llama-3.2-nv-embedqa-1b-v2 operates in `passage` or `query` mode, and thus require the `input_type` parameter. `passage` is used when generating embeddings during indexing. `query` is used when generating embeddings during querying. It is very important to use the correct `input_type`. Failure to do so will result in large drops in retrieval accuracy.","title":"Input Type"},"encoding_format":{"type":"string","description":"The format to return the embeddings in.","enum":["float","base64"],"default":"float","title":"Encoding Format"},"truncate":{"type":"string","description":"Specifies how inputs longer than the maximum token length of the model are handled. Passing `START` discards the start of the input. `END` discards the end of the input. In both cases, input is discarded until the remaining input is exactly the maximum input token length for the model. If `NONE` is selected, when the input exceeds the maximum input token length an error will be returned.","enum":["NONE","START","END"],"default":"NONE","title":"Truncate"},"user":{"type":"string","description":"Not implemented, but provided for API compliance. This field is ignored.","title":"User"}},"required":["input","model"]}}}},"x-nvai-meta":{"name":"Create Text Embedding","description":"Generates an embedding vector from the provided text\nusing a specified model. The embedding can be returned\nin either float array or base64-encoded format.\n","path":"create","examples":[{"name":"Embedding vector for text input","requestJson":"{\n \"input\": \"What is the capital of France?\",\n \"model\": \"nvidia/llama-3.2-nv-embedqa-1b-v2\",\n \"input_type\": \"query\",\n \"encoding_format\": \"float\",\n \"truncate\": \"NONE\"\n}\n","responseJson":"$a4"}],"templates":[{"title":"Synchronous requests","requestEjs":{"curl":"curl -X POST https://integrate.api.nvidia.com/v1/embeddings \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -d '{\n \"input\": [\"<%- request.input.replaceAll('\"', '\\\\\"').replaceAll(\"'\", \"'\\\"'\\\"'\") %>\"],\n \"model\": \"nvidia/llama-3.2-nv-embedqa-1b-v2\",\n \"input_type\": \"<%- request.input_type %>\",\n \"encoding_format\": \"<%- request.encoding_format %>\",\n \"truncate\": \"<%- request.truncate %>\"\n }'\n","python":"from openai import OpenAI\n\nclient = OpenAI(\n api_key=\"$NVIDIA_API_KEY\",\n base_url=\"https://integrate.api.nvidia.com/v1\"\n)\n\nresponse = client.embeddings.create(\n input=[<%- JSON.stringify(request.input) %>],\n model=\"nvidia/llama-3.2-nv-embedqa-1b-v2\",\n encoding_format=\"<%- request.encoding_format %>\",\n extra_body={\"input_type\": \"<%- request.input_type %>\", \"truncate\": \"<%- request.truncate %>\"}\n)\n\nprint(response.data[0].embedding)\n","langchain":"from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings\n\nclient = NVIDIAEmbeddings(\n model=\"nvidia/llama-3.2-nv-embedqa-1b-v2\", \n api_key=\"$NVIDIA_API_KEY\", \n truncate=\"<%- request.truncate %>\", \n )\n\nembedding = client.embed_query(<%- JSON.stringify(request.input) %>)\nprint(embedding)\n"},"response":"$a5"}]},"responses":{"200":{"description":"Successful response","content":{"application/json":{"schema":{"type":"object","properties":{"object":{"type":"string","example":"list"},"data":{"type":"array","items":{"$ref":"#/components/schemas/EmbeddingObject"}},"model":{"type":"string","example":"nvidia/llama-3.2-nv-embedqa-1b-v2"},"usage":{"type":"object","description":"Number of tokens","properties":{"prompt_tokens":{"type":"integer","example":0},"total_tokens":{"type":"integer","example":0}}}}}}}},"400":{"description":"Bad request","content":{"application/json":{"schema":{"type":"object","properties":{"object":{"type":"string"},"message":{"type":"string"},"detail":{"type":"object","additionalProperties":true},"type":{"type":"string"}}}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"EmbeddingObject":{"type":"object","properties":{"object":{"type":"string","example":"embedding"},"embedding":{"oneOf":[{"items":{"type":"number"},"type":"array","description":"The embedding vector as a list of floats. The length of the vector depends on the model."},{"type":"string","description":"The embedding vector as a Base64 string. The length of the string depends on the model."}]},"index":{"type":"integer","description":"The index of the embedding in the list of embeddings."}},"required":["object","embedding","index"]}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-24T23:53:37.986Z","nvcfFunctionId":"08d83ec3-339c-4923-b64c-2da76e684a14","createdDate":"2024-12-16T21:01:03.611Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_2-nv-embedqa-1b-v2","termsOfUse":"GOVERNING TERMS: This trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Community Model License. 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/nvidia/containers/llama-3.2-nv-embedqa-1b-v2"},"playground":{"type":"custom","input":{"items":[{"key":"input","type":"text-area"},{"key":"input_type","type":"select"},{"key":"encoding_format","type":"select"},{"key":"truncate","type":"select"}]},"parameters":{"omitProperties":["input_type","encoding_format","truncate"]},"output":{"items":[{"key":"data[0].embedding","type":"code","language":"javascript","formatAsJson":true}]},"requestBody":"{ \"input\": [\"<%- request.input %>\"], \"model\": \"nvidia/llama-3.2-nv-embedqa-1b-v2\", \"input_type\": \"<%- request.input_type %>\", \"encoding_format\": \"<%- request.encoding_format %>\", \"truncate\": \"<%- request.truncate %>\" }"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$a6"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$a7"}]},"artifactName":"llama-3_2-nv-embedqa-1b-v2"},"config":{"name":"llama-3_2-nv-embedqa-1b-v2","type":"model"}},{"endpoint":{"artifact":{"name":"nvclip","displayName":"nvclip","publisher":"nvidia","shortDescription":"NV-CLIP is a multimodal embeddings model for image and text.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nvclip.jpg","labels":["Computer vision","NVIDIA NIM","Run on rtx","multimodal embeddings","text and image"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","bias":"| Field | Response |\n| -- | -- |\n|Participation considerations from adversely impacted groups [(protected classes)](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None of the Above |\n| Measures taken to mitigate against unwanted bias: | Not Applicable |","canGuestDownload":true,"createdDate":"2024-06-13T20:35:52.208Z","description":"$a8","explainability":"$a9","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$aa","safetyAndSecurity":"| Field | Response |\n| -- | -- |\n| Model Application(s): | Image Search |\n| Describe the life-critical application (if present). | None: Not within Operational Design Domain |\n| Use Case Restrictions: | Abide by [https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/\"](https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/) |\n| Describe access restrictions (if any): | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. |","updatedDate":"2025-04-11T18:04:11.709Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"0269404d-5ae2-49e6-83a6-037d21e53351"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for nvidia/nvclip","description":"The NVIDIA NIM REST API. Please see https://docs.api.nvidia.com/nim 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":"NVIDIA AI Foundation Models Community License","url":"https://docs.nvidia.com/ai-foundation-models-community-license.pdf"}},"servers":[{"url":"https://integrate.api.nvidia.com/v1"}],"tags":[{"name":"NVIDIA NV-CLIP API","description":"Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms."}],"paths":{"/embeddings":{"post":{"tags":["Embeddings"],"summary":"Creates an embedding vector representing the input text or image.","description":"Invokes inference using the embedding 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":"createEmbedding","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":{"$ref":"#/components/schemas/EmbeddingsRequest"}}},"required":true},"x-nvai-meta":{"name":"Create Text Embedding","description":"Generates an embedding vector from the provided text\nusing a specified model. The embedding can be returned\nin either float array or base64-encoded format.\n","path":"create","templates":[{"title":"Synchronous requests","requestEjs":{"curl":"$ab","python":"$ac","node":"$ad"},"response":"$ae"}]},"responses":{"200":{"description":"Invocation is fulfilled.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/EmbeddingsResponse"}}}},"402":{"description":"Payment Required.","content":{"application/json":{"schema":{"properties":{"detail":{"type":"string","maxLength":256,"format":"^[a-zA-Z-]{1,64}$","description":"Contains specific information related to the error and why it occurred.","example":"You have reached your limit of credits."}},"type":"object","title":"PaymentRequiredError"}}}},"422":{"description":"Validation failed, provided entity could not be processed.","content":{"application/json":{"schema":{"$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/bc205f8e-1740-40df-8d32-c4321763498a","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}},"500":{"description":"The invocation ended with an error.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Errors"},"example":{"type":"urn:nvcf-worker-service:problem-details:internal-server-error","title":"Internal Server Error","status":500,"detail":"string","instance":"/v2/nvcf/pexec/functions/bc205f8e-1740-40df-8d32-c4321763498a","requestId":"3fa85f64-5717-4562-b3fc-2c963f66afa6"}}}}}}}},"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"EmbeddingsRequest":{"additionalProperties":false,"properties":{"input":{"oneOf":[{"type":"string","title":"string","example":"This is a test.","pattern":"^.*$"},{"type":"array","items":{"type":"string","pattern":"^.*$"},"maxItems":64}],"title":"Input","description":"The list of images or texts that you want to generate embeddings for. Images should be in form of `data:image/{format};base64,{base64encodedimage}`. If the size of an image is more than 200KB, it needs to be uploaded to a presigned S3 bucket using NVCF Asset APIs. Once uploaded you can refer to it using the following format: `

`. Accepted formats are `jpg`, `png` and `jpeg`.","examples":[["The quick brown fox jumped over the lazy dog","data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAAEElEQVR4nGK6HcwNCAAA//8DTgE8HuxwEQAAAABJRU5ErkJggg=="],["The quick brown fox jumped over the lazy dog","data:image/png;asset_id,87b132b0-08f9-43ea-8fab-f107350a5d00"]]},"encoding_format":{"type":"string","enum":["float","base64"],"title":"Encoding Format","description":"The format to return the embeddings in. Can be either `float` or `base64`.","default":"float"},"model":{"type":"string","enum":["nvidia/nvclip"],"title":"Model","description":"ID of the embedding model.","examples":["nvidia/nvclip"]},"dimensions":{"description":"Not implemented, but provided for API compliance. This field is ignored.\n","type":"integer","minimum":1,"maximum":1,"format":"int32"},"user":{"type":"string","description":"Not implemented, but provided for API compliance. This field is ignored.","pattern":"^.*$","maxLength":204800,"example":"user123"}},"type":"object","required":["input","model"],"title":"EmbeddingsRequest"},"EmbeddingsResponse":{"type":"object","properties":{"object":{"description":"The object type, which is always `list`.","enum":["list"],"title":"Object","type":"string"},"data":{"items":{"$ref":"#/components/schemas/Embedding"},"type":"array","title":"Data","description":"The list of embeddings generated by the model.","maxItems":128,"examples":[[{"embedding":[0.1,0.1,0.1],"index":0,"object":"embedding"},{"embedding":[0.1,0.1,0.1],"index":1,"object":"embedding"}]]},"model":{"type":"string","description":"Model used to generate embeddings.","example":"nvidia/nvclip","title":"Model","const":"nvidia/nvclip"},"usage":{"allOf":[{"$ref":"#/components/schemas/Usage"}],"description":"Usage statistics for the embeddings request.","examples":[{"num_images":1,"prompt_tokens":80,"total_tokens":80}]}},"required":["object","data","usage","model"],"title":"EmbeddingsResponse"},"Embedding":{"type":"object","description":"Represents an embedding vector returned by embedding endpoint.","properties":{"object":{"description":"The object type, which is always `embedding`.","enum":["embedding"],"title":"Object","type":"string"},"index":{"type":"integer","format":"int32","title":"Index","description":"The index of the embedding in the list of embeddings.","minimum":0,"maximum":127},"embedding":{"oneOf":[{"type":"array","description":"The embedding vector as a list of floats, The length of the vector depends on the model.\n","items":[{"type":"number"}],"maxItems":1024},{"type":"string","description":"The embedding vector as base64 string. The length of the vector depends on the model.\n","format":"^(?:[A-Za-z0-9+/]{4})*(?:[A-Za-z0-9+/]{4}|[A-Za-z0-9+/]{3}=|[A-Za-z0-9+/]{2}==)$"}]},"title":"Embedding"},"required":["index","object","embedding"],"title":"Embeddings"},"Usage":{"properties":{"num_images":{"type":"integer","format":"int32","title":"Num Images","minimum":0,"maximum":64,"description":"Number of images passed."},"prompt_tokens":{"type":"integer","format":"int32","title":"Prompt Tokens","description":"Number of tokens in the prompt.","minimum":77,"maximum":4928},"total_tokens":{"type":"integer","format":"int32","title":"Total Tokens","description":"Total number of tokens used in the request.","minimum":77,"maximum":4928}},"type":"object","required":["num_images","prompt_tokens","total_tokens"],"title":"Usage"},"Errors":{"properties":{"type":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error type"},"title":{"type":"string","format":"^.{1, 128}$","maxLength":128,"description":"Error title"},"status":{"type":"integer","format":"int32","minimum":100,"maximum":999,"description":"Error status code"},"detail":{"type":"string","format":"^.{1, 1024}$","maxLength":1024,"description":"Detailed information about the error"},"instance":{"type":"string","format":"^.{1, 256}$","maxLength":256,"description":"Function instance used to invoke the request"},"requestId":{"type":"string","format":"uuid","maxLength":36,"description":"UUID of the request"}},"type":"object","required":["type","title","status","detail","instance","requestId"],"title":"InvokeError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-04-11T18:04:12.307Z","nvcfFunctionId":"3072eebf-b0f0-4318-a5b8-5a45cd035b95","createdDate":"2024-06-13T20:35:52.529Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-nvclip","termsOfUse":"GOVERNING TERMS: GOVERNING TERMS: The trial service 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.\n","showUnavailableBanner":false,"cta":{"type":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$af"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$b0"}]},"artifactName":"nvclip"},"config":{"name":"nvclip","type":"model"}},{"endpoint":{"artifact":{"name":"paddleocr","displayName":"paddleocr","publisher":"baidu","shortDescription":"Model for table extraction that receives an image as input, runs OCR on the image, and returns the text within the image and its bounding boxes.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/paddleocr.jpg","labels":["Optical Character Detection","Optical Character Recognition","Table Extraction","data ingestion","extraction","nemo retriever","run on rtx"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-11-22T17:15:01.232Z","description":"$b1","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-25T00:02:36.704Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"ddf72525-d472-4882-821d-80e3e41c1401"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"PaddleOCR","description":"PaddleOCR","version":"0.2.1-rc0"},"paths":{"/v1/infer":{"post":{"summary":"Post Infer","operationId":"post_infer_v1_infer_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaddleOCRRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/PaddleOCRResponse"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Inference model on image","returns":"Returns a object list.\n","path":"create","examples":[{"name":"Image from example","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/paddle/paddleocr1.png"},"requestJson":"$b2","responseJson":"$b3"},{"name":"Image from example","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/paddle/paddleocr2.png"},"requestJson":"$b4","responseJson":"$b5"}],"templates":[{"title":"Default","requestEjs":{"python":"import requests, base64\n\ninvoke_url = \"https://ai.api.nvidia.com/v1/cv/baidu/paddleocr\"\n\nwith open(\"paddleocr1.png\", \"rb\") as f:\n image_b64 = base64.b64encode(f.read()).decode()\n\nassert len(image_b64) < 180_000, \\\n \"To upload larger images, use the assets API (see docs)\"\n\nheaders = {\n \"Authorization\": \"Bearer $NVIDIA_API_KEY\",\n \"Accept\": \"application/json\"\n}\n\npayload = {\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": f\"data:image/png;base64,{image_b64}\"\n }\n ]\n}\n\nresponse = requests.post(invoke_url, headers=headers, json=payload)\n\nprint(response.json())\n","node.js":"import axios from 'axios';\nimport { readFile } from 'node:fs/promises';\n\nconst invokeUrl = \"https://ai.api.nvidia.com/v1/cv/baidu/paddleocr\";\n\nconst headers = {\n \"Authorization\": \"Bearer $NVIDIA_API_KEY\",\n \"Accept\": \"application/json\"\n};\n\nreadFile(\"paddleocr1.png\")\n .then(data => {\n const imageB64 = Buffer.from(data).toString('base64');\n if (imageB64.length > 180_000) {\n throw new Error(\"To upload larger images, use the assets API (see docs)\");\n }\n\n const payload = {\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": `data:image/png;base64,${imageB64}`\n }\n ]\n };\n\n return axios.post(invokeUrl, payload, { headers: headers, responseType: 'json' });\n })\n .then(response => {\n console.log(JSON.stringify(response.data));\n })\n .catch(error => {\n console.error(error);\n });\n","curl":"image_b64=$( base64 -i paddleocr1.png )\n\naccept_header='Accept: application/json'\n\n# Construct the JSON payload\necho '{\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": \"data:image/png;base64,'\"${image_b64}\"'\"\n }\n ]\n}' > payload.json\n\ncurl https://ai.api.nvidia.com/v1/cv/baidu/paddleocr \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"$b6"}]}}},"/v1/health/live":{"get":{"summary":"Health Live","description":"Return service liveness status","operationId":"health_live_v1_health_live_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HealthLiveResponse"}}}}}}},"/v1/health/ready":{"get":{"summary":"Health Ready","description":"Return service readiness status","operationId":"health_ready_v1_health_ready_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HealthReadyResponse"}}}}}}},"/v1/metrics":{"get":{"summary":"Metrics","description":"Handler for metrics endpoint.","operationId":"metrics_v1_metrics_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"type":"string","title":"Response Metrics V1 Metrics Get"}}}}}}},"/v1/license":{"get":{"summary":"License","description":"Handler for license endpoint.","operationId":"license_v1_license_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/LicenseEndpointModel"}}}}}}},"/v1/metadata":{"get":{"summary":"Metadata","description":"Handler for metadata endpoint.","operationId":"metadata_v1_metadata_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/MetadataEndpointModel"}}}}}}},"/v1/manifest":{"get":{"summary":"Manifest","description":"Handler for the manifest endpoint.","operationId":"manifest_v1_manifest_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ManifestEndpointModel"}}}}}}}},"components":{"schemas":{"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"HealthLiveResponse":{"properties":{"live":{"type":"boolean","title":"Live"}},"type":"object","required":["live"],"title":"HealthLiveResponse"},"HealthReadyResponse":{"properties":{"ready":{"type":"boolean","title":"Ready"}},"type":"object","required":["ready"],"title":"HealthReadyResponse"},"Image":{"properties":{"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type","default":"image_url"},"image_url":{"$ref":"#/components/schemas/ImageUrl"}},"type":"object","required":["image_url"],"title":"Image"},"ImageUrl":{"properties":{"url":{"type":"string","title":"Url","description":"The URL of the image to be processed."}},"type":"object","required":["url"],"title":"ImageUrl"},"LicenseEndpointModel":{"properties":{"name":{"type":"string","title":"Name","description":"The name of the license for the NIM container."},"path":{"type":"string","title":"Path","description":"The filepath within the container containing the license content."},"sha":{"type":"string","title":"Sha","description":"A SHA1 hash of the license contents."},"size":{"type":"integer","title":"Size","description":"The number of characters in the license content."},"url":{"type":"string","title":"Url","description":"The url where this license is hosted externally."},"type":{"type":"string","enum":["file"],"const":"file","title":"Type","description":"The format of the license content."},"content":{"type":"string","title":"Content","description":"The license text."}},"type":"object","required":["name","path","sha","size","url","type","content"],"title":"LicenseEndpointModel","description":"A model representing the license response."},"ManifestEndpointModel":{"properties":{"manifest_file":{"type":"string","title":"Manifest File","description":"The content of the manifest file describing the required model artifacts."}},"type":"object","required":["manifest_file"],"title":"ManifestEndpointModel","description":"A model representing the manifest response."},"Message":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role","default":""},"content":{"items":{"$ref":"#/components/schemas/Image"},"type":"array","minItems":1,"title":"Content"}},"type":"object","required":["content"],"title":"Message"},"MetadataEndpointModel":{"properties":{"assetInfo":{"items":{"type":"string"},"type":"array","title":"Assetinfo","description":"A list of required container assets excluding model artifacts"},"licenseInfo":{"$ref":"#/components/schemas/LicenseEndpointModel","description":"The license info."},"modelInfo":{"items":{"$ref":"#/components/schemas/ModelInfo"},"type":"array","title":"Modelinfo","description":"A list of models being served by the NIM."},"version":{"type":"string","title":"Version","description":"The version of the NIM service."}},"type":"object","required":["assetInfo","licenseInfo","modelInfo","version"],"title":"MetadataEndpointModel","description":"A model representing the metadata response."},"ModelInfo":{"properties":{"modelUrl":{"type":"string","title":"Modelurl"},"shortName":{"type":"string","title":"Shortname"}},"type":"object","required":["modelUrl","shortName"],"title":"ModelInfo","description":"A model representing the model response."},"PaddleOCRRequest":{"properties":{"model":{"type":"string","enum":["baidu/paddleocr"],"const":"baidu/paddleocr","title":"Model Name","default":"baidu/paddleocr"},"messages":{"items":{"$ref":"#/components/schemas/Message"},"type":"array","maxItems":1,"minItems":1,"title":"Messages"}},"type":"object","required":["messages"],"title":"PaddleOCRRequest"},"PaddleOCRResponse":{"properties":{"object":{"type":"string","enum":["list"],"const":"list","title":"Object","default":"list"},"data":{"items":{"$ref":"#/components/schemas/PaddleOCRResponseItem"},"type":"array","title":"Data"},"model":{"type":"string","title":"Model"},"usage":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Usage"}},"type":"object","required":["data","model"],"title":"PaddleOCRResponse"},"PaddleOCRResponseItem":{"properties":{"index":{"type":"integer","title":"Index"},"content":{"type":"string","title":"Content"},"object":{"type":"string","enum":["string"],"const":"string","title":"Object","default":"string"}},"type":"object","required":["index","content"],"title":"PaddleOCRResponseItem"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-25T00:02:37.700Z","nvcfFunctionId":"43ace38a-357d-4440-9385-10a9d4c9a581","createdDate":"2024-11-22T17:15:01.822Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/ingestion/table-extraction/latest/api-reference.html","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the NVIDIA Evaluation License Agreement. Additional Information: Apache License Version 2.0.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$b7"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$b8"}]},"artifactName":"paddleocr"},"config":{"name":"paddleocr","type":"model"}},{"endpoint":{"artifact":{"name":"nv-yolox-page-elements-v1","displayName":"nv-yolox-page-elements-v1","publisher":"nvidia","shortDescription":"Model for object detection, fine-tuned to detect charts, tables, and titles in documents.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/nv-yolox-page-elements-v1.jpg","labels":["Chart Detection","Data ingestion","Object Detection","Table Detection","extraction","nemo retriever","run on rtx"],"attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"}],"artifactType":"ENDPOINT","canGuestDownload":true,"createdDate":"2024-11-22T17:15:01.485Z","description":"$b9","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","updatedDate":"2025-03-25T00:03:00.623Z"},"requestStatus":{"statusCode":"SUCCESS","requestId":"08c7165d-5534-4c62-985e-1829b4397400"}},"spec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NeMo Retriever YOLOX Structured Images v1","description":"You Only Look Once (YOLO) anchor-free object detection of charts and tables in structured images.","version":"0.2.1-rc0"},"paths":{"/v1/infer":{"post":{"summary":"Post V1 Infer","description":"Detect charts and tables in the provided images.","operationId":"post_v1_infer_v1_infer_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/YoloxRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/YoloxResponse"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"Inference model on image","returns":"Returns a object list.\n","path":"create","examples":[{"name":"Image from example","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/yolox/yolox1.jpg"},"requestJson":"$ba","responseJson":"$bb"},{"name":"Image from example","input":{"image":"https://assets.ngc.nvidia.com/products/api-catalog/yolox/yolox2.jpg"},"requestJson":"$bc","responseJson":"$bd"}],"templates":[{"title":"Default","requestEjs":{"python":"import requests, base64\n\ninvoke_url = \"https://ai.api.nvidia.com/v1/cv/nvidia/nv-yolox-page-elements-v1\"\n\nwith open(\"yolox1.png\", \"rb\") as f:\n image_b64 = base64.b64encode(f.read()).decode()\n\nassert len(image_b64) < 180_000, \\\n \"To upload larger images, use the assets API (see docs)\"\n\nheaders = {\n \"Authorization\": \"Bearer $NVIDIA_API_KEY\",\n \"Accept\": \"application/json\"\n}\n\npayload = {\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": f\"data:image/png;base64,{image_b64}\"\n }\n ]\n}\n\nresponse = requests.post(invoke_url, headers=headers, json=payload)\n\nprint(response.json())\n","node.js":"import axios from 'axios';\nimport { readFile } from 'node:fs/promises';\n\nconst invokeUrl = \"https://ai.api.nvidia.com/v1/cv/nvidia/nv-yolox-page-elements-v1\";\n\nconst headers = {\n \"Authorization\": \"Bearer $NVIDIA_API_KEY\",\n \"Accept\": \"application/json\"\n};\n\nreadFile(\"yolox1.png\")\n .then(data => {\n const imageB64 = Buffer.from(data).toString('base64');\n if (imageB64.length > 180_000) {\n throw new Error(\"To upload larger images, use the assets API (see docs)\");\n }\n\n const payload = {\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": `data:image/png;base64,${imageB64}`\n }\n ]\n };\n\n return axios.post(invokeUrl, payload, { headers: headers, responseType: 'json' });\n })\n .then(response => {\n console.log(JSON.stringify(response.data));\n })\n .catch(error => {\n console.error(error);\n });\n","curl":"image_b64=$( base64 -i yolox1.png )\n\naccept_header='Accept: application/json'\n\n# Construct the JSON payload\necho '{\n \"input\": [\n {\n \"type\": \"image_url\",\n \"url\": \"data:image/png;base64,'\"${image_b64}\"'\"\n }\n ]\n}' > payload.json\n\ncurl https://ai.api.nvidia.com/v1/cv/nvidia/nv-yolox-page-elements-v1 \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -H \"$accept_header\" \\\n -d @payload.json\n"},"response":"$be"}]}}},"/v1/health/live":{"get":{"summary":"Health Live","description":"Check if the service is running.","operationId":"health_live_v1_health_live_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HealthLiveResponse"}}}}}}},"/v1/health/ready":{"get":{"summary":"Health Ready","description":"Check if the service is ready to recieve traffic.","operationId":"health_ready_v1_health_ready_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HealthReadyResponse"}}}}}}},"/v1/metrics":{"get":{"summary":"Metrics","description":"Handler for metrics endpoint.","operationId":"metrics_v1_metrics_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"type":"string","title":"Response Metrics V1 Metrics Get"}}}}}}},"/v1/license":{"get":{"summary":"License","description":"Handler for license endpoint.","operationId":"license_v1_license_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/LicenseEndpointModel"}}}}}}},"/v1/metadata":{"get":{"summary":"Metadata","description":"Handler for metadata endpoint.","operationId":"metadata_v1_metadata_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/MetadataEndpointModel"}}}}}}},"/v1/manifest":{"get":{"summary":"Manifest","description":"Handler for the manifest endpoint.","operationId":"manifest_v1_manifest_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ManifestEndpointModel"}}}}}}}},"components":{"schemas":{"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"HealthLiveResponse":{"properties":{"live":{"type":"boolean","title":"Live"}},"type":"object","required":["live"],"title":"HealthLiveResponse"},"HealthReadyResponse":{"properties":{"ready":{"type":"boolean","title":"Ready"}},"type":"object","required":["ready"],"title":"HealthReadyResponse"},"LicenseEndpointModel":{"properties":{"name":{"type":"string","title":"Name","description":"The name of the license for the NIM container."},"path":{"type":"string","title":"Path","description":"The filepath within the container containing the license content."},"sha":{"type":"string","title":"Sha","description":"A SHA1 hash of the license contents."},"size":{"type":"integer","title":"Size","description":"The number of characters in the license content."},"url":{"type":"string","title":"Url","description":"The url where this license is hosted externally."},"type":{"type":"string","enum":["file"],"const":"file","title":"Type","description":"The format of the license content."},"content":{"type":"string","title":"Content","description":"The license text."}},"type":"object","required":["name","path","sha","size","url","type","content"],"title":"LicenseEndpointModel","description":"A model representing the license response."},"ManifestEndpointModel":{"properties":{"manifest_file":{"type":"string","title":"Manifest File","description":"The content of the manifest file describing the required model artifacts."}},"type":"object","required":["manifest_file"],"title":"ManifestEndpointModel","description":"A model representing the manifest response."},"MetadataEndpointModel":{"properties":{"assetInfo":{"items":{"type":"string"},"type":"array","title":"Assetinfo","description":"A list of required container assets excluding model artifacts"},"licenseInfo":{"$ref":"#/components/schemas/LicenseEndpointModel","description":"The license info."},"modelInfo":{"items":{"$ref":"#/components/schemas/ModelInfo"},"type":"array","title":"Modelinfo","description":"A list of models being served by the NIM."},"version":{"type":"string","title":"Version","description":"The version of the NIM service."}},"type":"object","required":["assetInfo","licenseInfo","modelInfo","version"],"title":"MetadataEndpointModel","description":"A model representing the metadata response."},"ModelInfo":{"properties":{"modelUrl":{"type":"string","title":"Modelurl"},"shortName":{"type":"string","title":"Shortname"}},"type":"object","required":["modelUrl","shortName"],"title":"ModelInfo","description":"A model representing the model response."},"Type":{"type":"string","enum":["chart","table","title"],"title":"Type"},"ValidationError":{"properties":{"loc":{"items":{"anyOf":[{"type":"string"},{"type":"integer"}]},"type":"array","title":"Location"},"msg":{"type":"string","title":"Message"},"type":{"type":"string","title":"Error Type"}},"type":"object","required":["loc","msg","type"],"title":"ValidationError"},"YoloxBoundingBox":{"properties":{"xmin":{"type":"number","title":"Xmin"},"ymin":{"type":"number","title":"Ymin"},"xmax":{"type":"number","title":"Xmax"},"ymax":{"type":"number","title":"Ymax"},"confidence":{"type":"number","title":"Confidence"}},"type":"object","required":["xmin","ymin","xmax","ymax","confidence"],"title":"YoloxBoundingBox"},"YoloxImage":{"properties":{"type":{"type":"string","enum":["image_url"],"const":"image_url","title":"Type","default":"image_url"},"image_url":{"$ref":"#/components/schemas/YoloxImageUrl"}},"type":"object","required":["image_url"],"title":"YoloxImage"},"YoloxImageUrl":{"properties":{"url":{"type":"string","title":"Url","description":"The URL of the image to be processed."}},"type":"object","required":["url"],"title":"YoloxImageUrl"},"YoloxMessage":{"properties":{"role":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Role","default":""},"content":{"items":{"$ref":"#/components/schemas/YoloxImage"},"type":"array","minItems":1,"title":"Content"}},"type":"object","required":["content"],"title":"YoloxMessage"},"YoloxRequest":{"properties":{"model":{"type":"string","enum":["nvidia/nv-yolox-structured-images-v1"],"const":"nvidia/nv-yolox-structured-images-v1","title":"Model","default":"nvidia/nv-yolox-structured-images-v1"},"messages":{"items":{"$ref":"#/components/schemas/YoloxMessage"},"type":"array","maxItems":1,"minItems":1,"title":"Messages"},"confidence_threshold":{"anyOf":[{"type":"number"},{"type":"null"}],"title":"Confidence Threshold","description":"Threshold for filtering low-confidence predictions","default":0.01},"nms_threshold":{"anyOf":[{"type":"number"},{"type":"null"}],"title":"Nms Threshold","description":"Threshold for filtering overlapping predictions via non-max suppression","default":0.5}},"type":"object","required":["messages"],"title":"YoloxRequest"},"YoloxResponse":{"properties":{"object":{"type":"string","enum":["list"],"const":"list","title":"Object","default":"list"},"data":{"items":{"items":{"$ref":"#/components/schemas/YoloxResponseItem"},"type":"array"},"type":"array","title":"Data"},"model":{"type":"string","title":"Model"},"usage":{"anyOf":[{"type":"object"},{"type":"null"}],"title":"Usage"}},"type":"object","required":["data","model"],"title":"YoloxResponse"},"YoloxResponseItem":{"properties":{"bboxes":{"items":{"$ref":"#/components/schemas/YoloxBoundingBox"},"type":"array","title":"Bboxes"},"type":{"$ref":"#/components/schemas/Type"}},"type":"object","required":["bboxes","type"],"title":"YoloxResponseItem"}}}},"namespace":"qc69jvmznzxy","updatedDate":"2025-03-25T00:03:03.075Z","nvcfFunctionId":"96d723c1-5970-49a2-917a-e799e078242d","createdDate":"2024-11-22T17:15:02.010Z","attributes":{"apiDocsUrl":"https://docs.nvidia.com/nim/ingestion/object-detection/latest/api-reference.html","termsOfUse":"GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service; and the use of this model is governed by the NVIDIA Evaluation License Agreement. Additional Information: Apache License Version 2.0.\n","showUnavailableBanner":false,"cta":{"text":"Apply to Self-Host","url":"https://www.nvidia.com/en-us/ai/nim-notifyme/"},"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$bf"},{"label":"Windows on RTX AI PCs (Beta)","filename":"wsl2.md","contents":"$c0"}]},"artifactName":"nv-yolox-page-elements-v1"},"config":{"name":"nv-yolox-page-elements-v1","type":"model"}}],"items":["$c1","$c2","$c3","$c4","$c5","$c6","$c7","$c8","$c9","$ca"],"params":{},"slotTitle":[["$","div",null,{"className":"mb-2 flex items-start gap-2 max-xs:justify-between","children":[["$","h2",null,{"className":"text-ml font-medium leading-body tracking-less text-manitoulinLightWhite mb-0","children":"AI Models for RTX AI PCs and Workstations"}],["$","$L26",null,{"href":"/search?q=run-on-rtx","children":[["$","$L52",null,{"children":["$","svg","arrow-right:fill",{"data-src":"https://brand-assets.cne.ngc.nvidia.com/assets/icons/3.1.0/fill/arrow-right.svg","height":"1em","width":"1em","display":"inline-block","data-icon-name":"arrow-right","data-cache":"disabled","color":"$undefined","className":"btn-icon"}]}],"View All"],"className":"inline-flex items-center justify-center gap-2 text-center font-sans font-medium leading-text flex-row-reverse btn-tertiary btn-sm btn-pill text-nowrap mt-[3px]"}]]}],["$","p",null,{"className":"text-md font-normal text-manitoulinLightGray mb-0","children":"Spanning language, speech, animation, content generation, and vision capabilities, run NVIDIA NIM microservices on your RTX AI PC."}]," "]}]