3b:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/1qxuqc9exftar.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/1dkt88qx1lnxv.js"],"PageMetadata"] 3d:I[536465,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/1qxuqc9exftar.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/1dkt88qx1lnxv.js"],"WorkflowContent"] 3f:I[580626,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/1qxuqc9exftar.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/1dkt88qx1lnxv.js"],"default"] 40:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/1qxuqc9exftar.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/1dkt88qx1lnxv.js"],"default"] 38:["$","$L3b",null,{"hasPartnerEndpoint":false}] 3e:T109b,Autonomous vehicle (AV) development is a continuous process, requiring repeated post-training to refine the end-to-end stack and add new capabilities. Post-training for specific tasks requires datasets targeted to that scenario—such as a highway curve in low-light conditions. To effectively curate such datasets, developers must search through petabytes of multimodal training data, an incredibly labor-intensive process that requires detailed annotations and high recall accuracy. NVIDIA Cosmos Dataset Search is a vector search workflow that rapidly accelerates the data labeling and processing pipeline for AV developers. It uses the Cosmos Embed NIM to enable semantic search, bypassing the need for human annotation and improving recall quality. It connects to [NVIDIA Cosmos Curator](https://github.com/nvidia-cosmos/cosmos-curate) to refine datasets and retrieve queried data with incredible efficiency and accuracy. By enabling rapid, precise discovery of targeted scenarios, AV developers can: * **Accelerate model post-training** by supplying rare or problematic cases for retraining and validation. * **Shorten feedback loops** for error diagnosis and model improvement, driving faster innovation and safer deployments. * **Reduce manual data triage** — transforming vast data lakes into actionable resources for both engineers and machine learning practitioners. * **Enhance overall safety and robustness** by making continuous, data-driven scenario mining a core part of the development lifecycle. ## Experience Walkthrough The overall experience is divided into the following parts: 1. Select data pipeline and collection 2. Specify query type (text, video, embedding) 3. Input query and choose number of desired results 4. Click "Run” to view results 5. Click “Download Now” to retrieve the blueprint ## Architecture Diagram ![Architecture Diagram](https://assets.ngc.nvidia.com/products/api-catalog/cosmos-dataset-search/diagram.jpg) ## What’s Included in the Blueprint ### Scripts - CLI ([client.py](https://github.com/NVIDIA-Omniverse-blueprints/cosmos-dataset-search/blob/main/src/visual_search/client/client.py)) for creating a collection and ingesting data. - Docker-Compose script for standalone deployment - Helm-chart for Kubernetes deployment ### Containers: - Cosmos Embed1 NIM container - Visual Search service container - UI service container ## Minimum System Requirements #### Hardware **Standalone Deployment** * H200, H100, H20 * A100 * L40S, L4, L20 **Kubernetes** * **Inference**: * H200, H100, H20 * A100 * L40S, L4, L20 * **Indexing:** * CUDA version 11+ * H200, H100, H20 * A100 * L40S, L4, L20 * **Search:** * GPU not required Note: B100, GB200, RTX 6000 are not yet supported by the blueprint. For the most up to date information refer to [Blueprint Docs](https://github.com/NVIDIA-Omniverse-blueprints/cosmos-dataset-search/blob/main/docs/docs/documentation.md) page. #### Software * Operating System: Ubuntu 20.04 or newer * NVIDIA Driver version: 535 or newer * NVIDIA CUDA® version: 12.4 or newer * NVIDIA Container Toolkit version: 1.15.0 or newer * Docker version: Docker version 26 or newer * Python Version 3.11+ ## Terms of Use Use of the software is governed by the [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement) and the [Product-Specific Terms for NVIDIA AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products). Use of the NVIDIA Cosmos-Embed1-224p model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Use of the dataset is governed by the [NVIDIA Autonomous Vehicle Dataset License Agreement](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA_Autonomous_Vehicle_Dataset_License_Agreement.pdf). ADDITIONAL INFORMATION: For the Cosmos-Embed1-224p model, [Apache 2.0](https://github.com/facebookresearch/perception_models/blob/main/LICENSE.PE) and [MIT License](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/mit.md).39:[["$","div",".2",{"className":"relative","children":["$L3c",["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L3d",null,{"artifact":{"artifactType":"BLUEPRINT","name":"cosmos-dataset-search","displayName":"Cosmos Dataset Search","publisher":"nvidia","shortDescription":"Accelerate post-training of end-to-end autonomous vehicle stacks with vector search and retrieval for large video datasets.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/cosmos-dataset-search.jpg","labels":["Autonomous Vehicles","Cosmos","Physical AI","Search","apiCatalogType:blueprint:apicatalogtype_enterprise_blueprint","blueprintType:blueprint:blueprinttype_nvidia_ai","data","industryType:blueprint:industrytype_physical_ai"],"attributes":[{"key":"ENTERPRISEREADY","value":"false"},{"key":"LAUNCHABLE","value":"false"},{"key":"PREVIEW","value":"false"}],"updatedDate":"2026-02-17T19:14:33.178Z","canGuestDownload":true,"createdDate":"2025-11-04T19:32:21.671Z","description":"$3e","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy"},"endpointName":"cosmos-dataset-search","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"Example - AI Virtual Assistant for Customer Service","description":"This API schema describes all the endpoints exposed by the AI Virtual Assistant for Customer Service NIM Blueprint","version":"1.0.0"},"paths":{"/agent/metrics":{"get":{"tags":["Health"],"summary":"Get Metrics","operationId":"get_metrics_agent_metrics_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{}}}}}}},"/agent/health":{"get":{"tags":["Health"],"summary":"Health Check","description":"Perform a Health Check\n\nReturns 200 when service is up. This does not check the health of downstream services.","operationId":"health_check_agent_health_get","responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HealthResponse"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"example":{"detail":"Internal server error occurred"}}}}}}},"/agent/generate":{"post":{"tags":["Agent"],"summary":"Generate Response","description":"Generate and stream the response to the provided prompt.","operationId":"generate_response_agent_generate_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/AgentRequest"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/AgentResponse"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"example":{"detail":"Internal server error occurred"}}}}},"x-nvai-meta":{"examples":[{"name":"What was my last purchase?","requestJson":"{\n \"user\": \"1\", \"api_type\": \"create_session\", \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What was my last purchase?\"\n }\n ],\n \"stream\": true\n}\n"},{"name":"What product did I order first?","requestJson":"{\n \"user\": \"1\", \"api_type\": \"create_session\", \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What product did I order first?\"\n }\n ],\n \"stream\": true\n}\n"}]}}}},"components":{"schemas":{"AgentRequest":{"properties":{"messages":{"anyOf":[{"items":{"$ref":"#/components/schemas/Message"},"type":"array","maxItems":50000},{"type":"null"}],"title":"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.","default":[]},"user_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"User Id","description":"A unique identifier representing your end-user.","default":""},"session_id":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Session Id","description":"A unique identifier representing the session associated with the response.","default":""},"api_type":{"type":"string","title":"Api Type","description":"The type of API action: 'create_session', 'end_session', 'generate', or 'summary'."}},"type":"object","required":["api_type"],"title":"AgentRequest","description":"Definition of the Prompt API data type."},"AgentResponse":{"properties":{"id":{"type":"string","maxLength":100000,"pattern":"[\\s\\S]*","title":"Id","default":""},"choices":{"items":{"$ref":"#/components/schemas/AgentResponseChoices"},"type":"array","maxItems":256,"title":"Choices","default":[]},"session_id":{"type":"string","title":"Session Id","description":"A unique identifier representing the session associated with the response."}},"type":"object","title":"AgentResponse","description":"Definition of Chain APIs resopnse data type"},"AgentResponseChoices":{"properties":{"index":{"type":"integer","maximum":256,"minimum":0,"format":"int64","title":"Index","default":0},"message":{"$ref":"#/components/schemas/Message","default":{"role":"assistant","content":""}},"finish_reason":{"type":"string","maxLength":4096,"pattern":"[\\s\\S]*","title":"Finish Reason","default":""},"sentiment":{"type":"string","title":"Sentiment","description":"Any sentiment associated with this message","default":""}},"type":"object","title":"AgentResponseChoices","description":"Definition of Chain response choices"},"HTTPValidationError":{"properties":{"detail":{"items":{"$ref":"#/components/schemas/ValidationError"},"type":"array","title":"Detail"}},"type":"object","title":"HTTPValidationError"},"HealthResponse":{"properties":{"message":{"type":"string","maxLength":4096,"pattern":"[\\s\\S]*","title":"Message","default":""}},"type":"object","title":"HealthResponse"},"Message":{"properties":{"role":{"type":"string","maxLength":256,"pattern":"[\\s\\S]*","title":"Role","description":"Role for a message AI, User and System","default":"user"},"content":{"type":"string","maxLength":131072,"pattern":"[\\s\\S]*","title":"Content","description":"The input query/prompt to the pipeline.","default":"I am going to Paris, what should I see?"}},"type":"object","title":"Message","description":"Definition of the Chat Message 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"}}},"tags":[{"name":"Health","description":"APIs for checking and monitoring server liveliness and readiness."},{"name":"Agent","description":"Core APIs for interacting with the agent."}]},"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T20:30:06.345Z","nvcfFunctionId":"b31cb137-8c05-4bcb-b8ee-c6ab53ac3acc","createdDate":"2026-02-17T19:14:33.411Z","attributes":{"apiDocsUrl":"NOT REQUIRED","termsOfUse":"GOVERNING TERMS: Use of this trial service is governed by the NVIDIA API Trial Terms of Service. Use of the NVIDIA Cosmos-Embed1 model is governed by the NVIDIA Community Model License. Use of the dataset is governed by the NVIDIA Autonomous Vehicle Dataset License Agreement. ADDITIONAL INFORMATION: Use of the Cosmos-Embed1 model is governed by Apache 2.0 and MIT License.\n","showUnavailableBanner":false,"cta":{"text":"Download Now","url":"https://github.com/NVIDIA-Omniverse-blueprints/cosmos-dataset-search/"}},"artifactName":"cosmos-dataset-search"},"hostedModels":[],"isLoginRequired":true,"playgroundElement":"$3f","publisherName":"nvidia","searchParams":{"model":"cosmos-dataset-search"},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/cosmos-dataset-search","aliases":["/nvidia/cosmos-dataset-search/experience"]},{"label":"Blueprint Card","icon":"book","kind":"default","id":"blueprintcard","href":"/nvidia/cosmos-dataset-search/blueprintcard","aliases":"$undefined"}]}]}]}]]}]] 3a:["$","$L40",null,{"spec":"$39:0:props:children:1:props:children:props:children:props:endpointSpec"}]