NVIDIA AI Blueprints
- 1.6k followers
- United States of America
- https://build.nvidia.com/nim/agent-blueprints
Popular repositories Loading
-
video-search-and-summarization
video-search-and-summarization PublicNVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automate…
-
deep-researcher-agent
deep-researcher-agent PublicThe NVIDIA Deep Researcher Agent Blueprint is an open reference example for building intelligent AI agents that connect to your enterprise data, reason using state-of-the-art models, and deliver tr…
-
pdf-to-podcast
pdf-to-podcast PublicTransform PDFs into AI podcasts for engaging on-the-go audio content.
-
portfolio-optimization
portfolio-optimization PublicPowered by NVIDIA cuOpt: a GPU-accelerated portfolio optimization toolkit for building, backtesting, and scaling Mean-CVaR and Mean-Variance investment workflows with CUDA-X Data Science.
-
llm-router
llm-router PublicRoute LLM requests to the best model for the task at hand.
Repositories
- nemotron-voice-agent Public
Reference implementation of an end-to-end voice agent built using the NVIDIA Nemotron models
- video-search-and-summarization Public
NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.
- Multi-Agent-Intelligent-Warehouse Public
An open blueprint for intelligent warehouse operations, combining agentic AI, governed warehouse state, decision intelligence, and controlled execution. Agents analyze & propose actions, while deterministic policy, approval, validation, execution layers preserve safety, authority, & auditability.
- portfolio-optimization Public
Powered by NVIDIA cuOpt: a GPU-accelerated portfolio optimization toolkit for building, backtesting, and scaling Mean-CVaR and Mean-Variance investment workflows with CUDA-X Data Science.
- Retail-Agentic-Commerce Public
Reference implementation of the Agentic Commerce Protocol (ACP) and Universal Commerce Protocol (UCP)- enabling AI-powered checkout negotiation while maintaining merchant control.
- transaction-foundation-model Public
- retail-shopping-assistant Public
The Retail Shopping Assistant is an AI-powered blueprint that provides a comprehensive interface for an intelligent retail shopping advisor. Built with LangGraph for agent orchestration, it features multi-agent architecture, real-time streaming responses, image-based search, and intelligent shopping cart management.
- nsight-copilot Public
-
