#67 · Primary category： LLM Application Frameworks
GenerativeAIExamples
Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.
Project last updated：08/20/26
GitHub Stars
4.2K
Forks
1.1K
Contributors
89
License
Apache-2.0
Why we included this project
NVIDIA's GenerativeAIExamples is less a single product and more a set of working recipes for anyone building generative AI on NVIDIA hardware. The repo collects reference workflows for RAG, agentic tool-calling, fine-tuning, evaluation, and guardrailing, nearly all of it built around NIMs and NeMo microservices. The notebooks show concrete setups: pointing RAG at a locally deployed NIM, assembling knowledge-graph retrieval, or running several guardrails in parallel to cut latency. Teams wanting to confirm how the NVIDIA pieces fit together before committing to an architecture can lift the patterns they need rather than start from scratch, and the accompanying notes make it easier to port them into your own microservice layout.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform