# NVIDIA/GenerativeAIExamples

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

Repository: https://github.com/NVIDIA/GenerativeAIExamples
Canonical: https://ross.abutalabs.com/products/generativeaiexamples
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: gpu-acceleration, large-language-models, llm, llm-inference, microservice, nemo, rag, retrieval-augmented-generation, tensorrt, triton-inference-server
Last push: 2026-08-20T04:15:27+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 8, longevity 74
- inputs: {"age_days": 1049, "days_push": 13, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4160, forks 1094 (observed 2026-08-28T04:08:37.424866+00:00)

## What it is
A collection of NVIDIA reference workflows, notebooks, and example projects for building generative AI systems on accelerated infrastructure. It covers RAG pipelines, agentic workflows, fine-tuning, and guardrailing using NVIDIA NIM, NeMo, TensorRT, and Triton microservices.

## Use cases
- build a RAG pipeline with NVIDIA NIM microservices
- deploy LLM inference on GPU with TensorRT and Triton
- fine-tune and evaluate LLMs with NeMo microservices
- create an agentic RAG workflow with Llama 3.1
- build knowledge graph RAG on GPU
- add guardrails and safety auditing to LLM apps
- learn to integrate NVIDIA AI endpoints with LangChain

## When to choose
- you are building RAG or agentic applications on NVIDIA GPUs
- you want reference architectures using NIM, NeMo, TensorRT, or Triton
- you need worked Jupyter notebook tutorials for NVIDIA's generative AI stack

## When to avoid
- you need a production-ready application rather than examples and tutorials
- you have no NVIDIA GPU or access to NVIDIA AI services
- you want a framework-agnostic stack without NVIDIA dependencies

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, llm-inference, agent-framework, llm-training, gpu-computing, microservices
- domain: large-language-models, deep-learning, developer-tools
- platform: python, cloud, self-hosted
- tags: nvidia-nim, tensorrt-llm, triton-inference-server, nemo, reference-workflows, jupyter-notebooks, microservice-architecture, retrieval-augmented-generation, ai-agents, gpu, docker

## Member repositories
- NVIDIA/GenerativeAIExamples (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:37.424866+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:22:49.191620+00:00, confidence not recorded.
  - readme: https://github.com/NVIDIA/GenerativeAIExamples (fetched 2026-08-28T04:08:37.424866+00:00, sha 2e6d49fbc8a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.