mrdbourke/simple-local-rag resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1011 stars · 303 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A tutorial repository by mrdbourke teaching how to build a retrieval-augmented generation (RAG) pipeline from scratch that runs entirely locally on an NVIDIA GPU. It walks through PDF ingestion, chunking, embedding with sentence transformers, semantic search, and LLM-based answer generation, culminating in a 'chat with PDF' style app called NutriChat.

Use cases

• build a rag pipeline from scratch
• chat with pdf documents locally
• learn how retrieval augmented generation works
• run an llm question answering system on my own gpu
• embed pdf text and search it semantically
• follow a hands-on rag tutorial with jupyter notebooks

When to choose

• you want to learn RAG concepts by building a complete pipeline yourself
• you have an NVIDIA GPU (5GB+ VRAM) or Google Colab access and want everything running locally without paid APIs
• you prefer open-source tools like PyTorch, sentence-transformers, and open LLMs over proprietary services

When to avoid

• you need a production-ready, maintained RAG framework rather than educational notebook code
• you have no NVIDIA GPU and cannot use Colab
• you need a polished application with setup docs and support - the repo has incomplete setup instructions and no license

Facets

learning-resource · maturity active

rag llm-inference pdf machine-learning nlp large-language-models tutorials artificial-intelligence pdf python cross-platform tutorial jupyter-notebook chat-with-pdf local-llm sentence-transformers pytorch open-source-llm retrieval-augmented-generation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="mrdbourke/simple-local-rag")