Skip to main content
Ctrl+K
 NVIDIA-RAG-blueprint - Home  NVIDIA-RAG-blueprint - Home

NVIDIA-RAG-blueprint

  • GitHub
 NVIDIA-RAG-blueprint - Home  NVIDIA-RAG-blueprint - Home

NVIDIA-RAG-blueprint

  • GitHub

Table of Contents

NVIDIA RAG Blueprint

  • Overview
  • Release Notes
  • Support Matrix

Get Started

  • Get an API Key
  • Deploy with Docker (Self-Hosted Models)
  • Web User Interface
  • Notebooks

Deployment Options for RAG Blueprint

  • Deploy with Docker (NVIDIA-Hosted Models)
  • Deploy on Kubernetes with Helm
  • Deploy on Kubernetes with Helm from the repository
  • Deploy on Kubernetes with Helm and MIG Support
  • Deploy on Kubernetes with NIM Operator

Common configurations

  • Best Practices for Common Settings
  • Change the LLM or Embedding Model
  • Customize LLM Parameters at Runtime
  • Customize Prompts
  • Model Profiles for Hardware Configurations
  • Multi-Collection Retrieval
  • Multi-Turn Conversation Support
  • Query rewriting to improve the accuracy of multi-turn conversations
  • Reasoning in Nemotron LLM model
  • Self-reflection to improve accuracy
  • Summarization

Data Ingestion & Processing

  • Audio Ingestion Support
  • Custom metadata Support
  • File System Access to Extraction Results
  • Multimodal Embedding Support (Early Access)
  • NeMo Retriever OCR for Enhanced Text Extraction (Early Access)
  • PDF Extraction with Nemoretriever Parse
  • Enable Text-Only Ingestion Support in Docker for NVIDIA RAG Blueprint
  • Deploy NV-Ingest Standalone

Vector Database and Retrieval

  • Configure Elasticsearch as Your Vector Database for NVIDIA RAG Blueprint
  • Enable Hybrid Search Support for NVIDIA RAG Blueprint
  • Milvus Configuration
  • Query Decomposition

Multimodal and Advanced Generation

  • Image captioning support for ingested documents
  • VLM based inferencing in RAG

Governance

  • NeMo Guardrails for input/output

Observability and Telemetry

  • Observability

Troubleshoot RAG Blueprint

  • Troubleshoot
  • RAG Pipeline Debugging Guide
  • Migrate from a Previous Version

Reference

  • Use the Python Package
  • Milvus Collection Schema Requirements
  • API - Ingestor Server Schema
  • API - RAG Server Schema

NVIDIA RAG Blueprint Documentation#

Welcome to the NVIDIA RAG Blueprint documentation. You can learn more here, including how to get started with the RAG Blueprint, how to customize the RAG Blueprint, and how to troubleshoot the RAG Blueprint.

  • To view this documentation on docs.nvidia.com, browse to NVIDIA RAG Blueprint Documentation.

  • To view this documentation on GitHub, browse to NVIDIA RAG Blueprint Documentation.

next

Minimum System Requirements for NVIDIA RAG Blueprint

NVIDIA NVIDIA
Privacy Policy | Manage My Privacy | Do Not Sell or Share My Data | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2025, NVIDIA Corporation.