Logo

RAG Pipelines for Developers

  • About the RAG Pipelines
  • Support Matrix
  • API Catalog Models
  • Query Decomposition
  • Structured Data
  • Multimodal Data
  • Multi-turn
  • Sample Chat Application
  • Alternative Vector Database
  • NIM for LLMs
  • Developing Simple Examples

Tools

  • Evaluation
  • Observability

Jupyter Notebooks

  • Press Release Chat Bot
  • NVIDIA API Catalog with LangChain
  • LangChain with Local Llama 2 Model
  • NVIDIA API Catalog, LlamaIndex, and LangChain
  • HF Checkpoints with LlamaIndex and LangChain
  • Multimodal Models from NVIDIA AI Catelog and AI Catalog with LangChain Agent
  • Build a RAG chain by generating embeddings for NVIDIA Triton documentation
  • LangGraph Handling LangChain Agent Intermediate_Steps
  • Notebook: Chatting with NVIDIA Financial Reports
  • Build a RAG using a locally hosted NIM

Software Components

  • Architecture
  • RAG Playground Web Application
  • Jupyter Notebook Server
  • Chain Server
  • Software Component Configuration
NVIDIA Generative AI Examples
  • »
  • Search

© Copyright 2023-2024, NVIDIA Corporation.