NVIDIA AI Blueprints
Official@nvidia-ai-blueprints · United States of America
NVIDIA AI Blueprints are reference examples that illustrate how NVIDIA NIM can be leveraged to build innovative solutions.
Agent Skills by NVIDIA AI Blueprints
Showing 23 vetted skills indexed across 2 GitHub repositories.
NVIDIA-AI-Blueprintsvss-deploy-profile
Deploy, verify, debug, and tear down NVIDIA VSS Docker Compose profiles on GPU hosts.
NVIDIA-AI-Blueprintsvss-deploy-detection-tracking-2d
Deploy, debug, and operate the RTVI-CV 2D detection and tracking microservice via Docker and REST API.
NVIDIA-AI-Blueprintsvss-summarize-video
Summarize recorded video clips via the LVS microservice with a VLM fallback.
NVIDIA-AI-Blueprintsvss-generate-video-report-rag
Generates VSS video summary reports with LVS HITL and Enterprise RAG document grounding.
NVIDIA-AI-Blueprintsvss-generate-video-calibration
Run AutoMagicCalib camera calibration on MP4 files, RTSP streams, or sample datasets via REST API.
NVIDIA-AI-Blueprintsvss-setup-behavior-analytics
Deploy the vss-behavior-analytics container standalone with chosen entrypoint, config, and calibration.
NVIDIA-AI-Blueprintsvss-manage-alerts
Manage VSS alert pipelines including subscriptions, Slack notifications, and incident queries.
NVIDIA-AI-Blueprintsvss-deploy-dense-captioning
Deploy the standalone RT-VLM dense-captioning microservice and exercise its REST API endpoints.
NVIDIA-AI-Blueprintsvss-generate-video-report
Generate structured video analysis and incident-range reports from NVIDIA VSS clips and analytics.
NVIDIA-AI-Blueprintsvss-deploy-detection-tracking-3d
Deploy the RTVI-CV-3D MV3DT microservice for multi-camera 3D detection and tracking.
NVIDIA-AI-Blueprintsvss-deploy-video-embedding
Deploy and operate the VSS RT-Embed video embedding microservice via Docker Compose.
NVIDIA-AI-Blueprintsvss-search-archive
Run natural-language fusion search over archived video and ingest files or RTSP streams for indexing.
NVIDIA-AI-Blueprintsbdd-container-update
Rebuilds and pushes the BDD test Docker image and updates its tag in start_test.sh.
NVIDIA-AI-Blueprintscufolio
Optimize stock portfolios with GPU-accelerated Mean-CVaR and Mean-Variance workflows.
NVIDIA-AI-Blueprintsvss-frag
Generate video summary reports using Long Video Summarization and Milvus knowledge retrieval.
NVIDIA-AI-Blueprintsvios
Manage video sensors and streams via VIOS REST API calls.
NVIDIA-AI-Blueprintsdeploy
Automate deployment, validation, and teardown of NVIDIA VSS profiles with Docker Compose.
NVIDIA-AI-Blueprintsvideo-analytics
Retrieve video incidents, alerts, and metrics from Elasticsearch.
NVIDIA-AI-Blueprintsrt-vlm
Deploys the VLM service for real-time video captioning and incident detection.
NVIDIA-AI-Blueprintsalerts
Manage and monitor video alerts via the VSS agent's natural-language interface.
NVIDIA-AI-Blueprintsvideo-understanding
Analyze video frames to answer visual content questions via the VSS agent.
NVIDIA-AI-Blueprintsvideo-search
Search stored videos by natural language queries for objects, actions, or events.
NVIDIA-AI-Blueprintsreport
Generate timestamped captioned video summaries via VSS REST API queries.
Frequently Asked Questions About NVIDIA AI Blueprints
FAQPage SchemaWhat specific tasks can be performed using these reference architectures?▼
These architectures enable real-time video captioning, incident detection, and natural-language searching of video archives. Additionally, they support financial modeling tasks, specifically calculating Mean-CVaR and Mean-Variance metrics for stock portfolios using accelerated computing resources.
Which technical personas are these reference architectures designed for?▼
These resources are intended for computer vision engineers, data scientists, and quantitative analysts. They provide structured reference implementations for developers building production-grade video intelligence systems or high-performance financial modeling environments.
What are the runtime requirements for deploying these reference examples?▼
Deployment requires a containerized environment utilizing Docker Compose for service orchestration. Users must manage video sensor streams via REST interfaces and ensure connectivity to Elasticsearch for metric storage and Milvus for vector-based knowledge retrieval.