liu673/rag-all-techniques
A collection of Jupyter notebooks implementing various RAG techniques from basic retrieval to advanced reranking, using openai, numpy, and fitz with detailed Chinese explanations.
Not currently ranked — collecting fresh signals.
star history
This repository provides hands-on implementations of multiple RAG techniques including semantic chunking, context enrichment, document augmentation, query transformation, and reranking. It avoids heavy frameworks like LangChain or FAISS, instead using direct Python libraries (openai, numpy, fitz/pymupdf) for educational clarity. Each notebook is designed to be readable, modifiable, and runnable, serving as a practical learning resource for understanding how RAG systems work.
Frequently asked
- What is liu673/rag-all-techniques?
- A collection of Jupyter notebooks implementing various RAG techniques from basic retrieval to advanced reranking, using openai, numpy, and fitz with detailed Chinese explanations.
- Is rag-all-techniques open source?
- Yes — liu673/rag-all-techniques is open source, released under the MIT license.
- What language is rag-all-techniques written in?
- liu673/rag-all-techniques is primarily written in Jupyter Notebook.
- How popular is rag-all-techniques?
- liu673/rag-all-techniques has 470 stars on GitHub.
- Where can I find rag-all-techniques?
- liu673/rag-all-techniques is on GitHub at https://github.com/liu673/rag-all-techniques.