GH Repository · pguso
rag-from-scratch
Demystify RAG by building it from scratch. Local LLMs, no black boxes — real understanding of embeddings, vector search, retrieval, and context-augmented generation.
- stars
- 1,630
- 30-day movement
- +31/day
- Related entries
- 60
- Connections
- 1
JavaScriptnodetutorialrag-pipelinerag-chatbotagent-appragnode-llama-cppnodejseducationalai-agentsllmagents
A JavaScript/Node.js tutorial project that builds a RAG (retrieval-augmented generation) pipeline from scratch using node-llama-cpp with local LLMs. It walks through embeddings, vector search, retrieval, and context-augmented generation without hiding the internals behind a framework.
You want to actually understand how RAG works rather than treating it as a black box.
Use it to
- Learn how RAG pipelines work step by step
- Run a local LLM chatbot with retrieval
- Study embeddings and vector search in Node.js
- Use as a starting point for a custom RAG chatbot
For Node.js developers learning RAG concepts hands-on
- Role
- agent-app
- Language
- JavaScript
- Licence
- MIT
- Forks
- 195
- Last push
- 2026-03-11
topicsragtutorialeducationalllmnodejsvector-search