This repository is a starting point for developers looking to integrate with the NVIDIA software ecosystem to speed up their generative AI systems. Whether you are building RAG pipelines, agentic workflows, or fine-tuning models, this repository will help you integrate NVIDIA, seamlessly and natively, with your development stack.

• What's New?
  • Data Flywheel
  • Safer Agentic AI
  • Knowledge Graph RAG
  • Agentic Workflows with Llama 3.1
  • RAG with Local NIM Deployment and LangChain
  • Vision NIM Workflows
• Try it Now!
• Data Flywheel
  • Tool-Calling Notebooks
• RAG
  • RAG Notebooks
  • RAG Examples
  • RAG Tools
  • RAG Projects
• Documentation
  • Getting Started
  • How To's
  • Reference
• Community

These tutorials demonstrate Data Flywheel workflows that use NVIDIA NeMo Microservices. They include components such as NVIDIA NeMo Datastore, NeMo Entity Store, NeMo Customizer, NeMo Evaluator, NeMo Guardrails microservices, and NVIDIA NIMs.

• Tool Calling Fine-tuning, Inference, Evaluation, and Guardrailing with NVIDIA NeMo Microservices and NIMs
• Embedding Fine-tuning, Inference, and Evaluation with NVIDIA NeMo Microservices and NIMs

The following tutorials illustrate how to audit your large language models with NeMo Auditor to identify vulnerabilities to unsafe prompts, and how to run inference with multiple rails in parallel to reduce latency and improve throughput.

• Audit your LLMs
• Inference with Parallel Rails

This example implements a GPU-accelerated pipeline for creating and querying knowledge graphs using RAG by leveraging NIM microservices and the RAPIDS ecosystem to process large-scale datasets efficiently.

• Knowledge Graphs for RAG with NVIDIA AI Foundation Models and Endpoints

• Build an Agentic RAG Pipeline with Llama 3.1 and NVIDIA NeMo Retriever NIM microservices [Blog, Notebook]
• NVIDIA Morpheus, NIM microservices, and RAG pipelines integrated to create LLM-based agent pipelines

• Tips for Building a RAG Pipeline with NVIDIA AI LangChain AI Endpoints by Amit Bleiweiss. [Blog, Notebook]

For more information, refer to the Generative AI Example releases.

A collection of Jupyter notebooks, sample code and reference applications built with Vision NIMs.

To pull the vision NIM workflows, clone this repository recursively:

git clone https://github.com/nvidia/GenerativeAIExamples --recurse-submodules

The workflows will then be located at GenerativeAIExamples/vision_workflows

Follow the links below to learn more:

• Learn how to use VLMs to automatically monitor a video stream for custom events.
• Learn how to search images with natural language using NV-CLIP.
• Learn how to combine VLMs, LLMs and CV models to build a robust text extraction pipeline.
• Learn how to use embeddings with NVDINOv2 and a Milvus VectorDB to build a few shot classification model.

Experience NVIDIA RAG Pipelines with just a few steps!

1. Get your NVIDIA API key.

   1. Go to the NVIDIA API Catalog.
   2. Select any model.
   3. Click Get API Key.
   4. Run:

      export NVIDIA_API_KEY=nvapi-...

2. Clone the repository.

   git clone https://github.com/nvidia/GenerativeAIExamples.git

3. Build and run the basic RAG pipeline.

   cd GenerativeAIExamples/RAG/examples/basic_rag/langchain/
   docker compose up -d --build

4. Go to https://localhost:8090/ and submit queries to the sample RAG Playground.

5. Stop containers when done.

   docker compose down

A Data Flywheel is a self-reinforcing cycle where user interactions generate data that improves AI models or products, leading to better outcomes that attract more users and further enhance data quality. This feedback loop relies on continuous data processing, model refinement, and guardrails to ensure accuracy and compliance while compounding value over time. Real-world applications range from personalized customer experiences to operational systems like inventory management, where improved predictions drive efficiency and growth.

Tool calling empowers Large Language Models (LLMs) to integrate with external APIs, execute dynamic workflows, and retrieve real-time data beyond their training scope. The NVIDIA NeMo microservices platform offers a modular infrastructure for deploying AI pipelines that includes fine-tuning, evaluation, inference, and guardrail enforcement—across Kubernetes clusters in cloud or on-premises environments.

This end-to-end tutorial demonstrates how to leverage NeMo Microservices to customize Llama-3.2-1B-Instruct by using the xLAM function-calling dataset, assess its accuracy, and implement safety constraints to govern its behavior.

NVIDIA has first-class support for popular generative AI developer frameworks like LangChain, LlamaIndex, and Haystack. These end-to-end notebooks show how to integrate NIM microservices using your preferred generative AI development framework.

Use these notebooks to learn about the LangChain and LlamaIndex connectors.

• RAG
  • Basic RAG with CHATNVIDIA LangChain Integration
  • RAG using local NIM microservices for LLMs and Retrieval
  • RAG for HTML Documents
  • Chat with NVIDIA Financial Reports
• Agents
  • NIM Tool Calling 101
  • Agentic RAG with NeMo Retriever
  • Agents with Human in the Loop

• Basic RAG with LlamaIndex Integration

By default, these end-to-end examples use preview NIM endpoints on NVIDIA API Catalog. Alternatively, you can run any of the examples on premises.

• LangChain example
• LlamaIndex example

• Multi-Turn
• Multimodal Data
• Structured Data (CSV)
• Query Decomposition

Example tools and tutorials to enhance LLM development and productivity when using NVIDIA RAG pipelines.

• Evaluation
• Observability

• NVIDIA Tokkio LLM-RAG: Use Tokkio to add avatar animation for RAG responses.
• Hybrid RAG Project on AI Workbench: Run an NVIDIA AI Workbench example project for RAG.

• Prerequisites

• Changing the Inference or Embedded Model
• Customizing the Vector Database
• Customizing the Chain Server:
  • Chunking Strategy
  • Prompting Template Engineering
• Configuring LLM Parameters at Runtime
• Supporting Multi-Turn Conversations
• Speaking Queries and Listening to Responses with NVIDIA Riva

• Support Matrix
• Architecture
• Using the Sample Chat Web Application
• RAG Playground Web Application
• Software Component Configuration

We're posting these examples on GitHub to support the NVIDIA LLM community and facilitate feedback. We invite contributions! Open a GitHub issue or pull request! See contributing Check out the community examples and notebooks.