GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

What is GenerativeAIExamples?

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

Overview of GenerativeAIExamples

What it is

This repository provides generative AI reference workflows optimized for accelerated infrastructure and microservice architecture. It is a starting point for developers integrating with the NVIDIA software ecosystem to build generative AI systems, including RAG pipelines, agentic workflows, and fine-tuning models.

Key features

  • Data Flywheel workflows using NVIDIA NeMo Microservices for fine-tuning, inference, evaluation, and guardrailing - Safer Agentic AI tutorials for auditing LLMs with NeMo Auditor and running inference with parallel rails - Knowledge Graph RAG pipeline leveraging GPU acceleration, NIM microservices, and the RAPIDS ecosystem - Agentic RAG pipeline with Llama 3.1 and NVIDIA NeMo Retriever NIM microservices - RAG with local NIM deployment and LangChain integration - Vision NIM workflows for video monitoring, image search, text extraction, and few-shot classification

Use cases

Developers can use these examples to build RAG pipelines, create agentic workflows, fine-tune large language models, integrate with NVIDIA NIM microservices, and deploy generative AI applications on accelerated infrastructure. The repository supports both cloud and on-premises deployments.

Getting started

  1. Get your NVIDIA API key from the NVIDIA API Catalog and export it: console export NVIDIA_API_KEY=nvapi-... 2. Clone the repository: console git clone https://github.com/nvidia/GenerativeAIExamples.git 3. Build and run the basic RAG pipeline: console cd GenerativeAIExamples/RAG/examples/basic_rag/langchain/ docker compose up -d --build 4. Stop containers when done: console docker compose down

License and pricing

The repository is licensed under Apache-2.0 and is open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/nvidiagenerativeaiexamples.svg)](https://yunodb.com/tools/nvidiagenerativeaiexamples?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/nvidiagenerativeaiexamples?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/nvidiagenerativeaiexamples.svg" alt="Featured on YunoDB" height="20"></a>