liu673/rag-all-techniques
Implementation of all RAG techniques in a simpler way（以简单的方式实现所有 RAG 技术）
Implements 17+ RAG techniques (semantic chunking, query transformation, reranking, graph-based retrieval, etc.) using standard Python libraries (OpenAI, NumPy, PyMuPDF) rather than framework abstractions like LangChain or FAISS. Each technique includes fully-commented notebook implementations demonstrating the complete pipeline from document ingestion through embedding creation, semantic search, and LLM-based response generation. Covers advanced patterns including adaptive retrieval strategy selection, self-evaluating RAG with relevance assessment, hybrid vector/BM25 fusion, and iterative feedback loops for continuous optimization.
453 stars. No commits in the last 6 months.
Stars
453
Forks
114
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/liu673/rag-all-techniques"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
bragai/bRAG-langchain
Everything you need to know to build your own RAG application
guyernest/advanced-rag
Jupyter Notebooks for Mastering LLM with Advanced RAG Course
FareedKhan-dev/rag-ecosystem
Understand and code every important component of RAG architecture
FareedKhan-dev/14-rag-failures
Encountering 14 different Naive RAG fails and using KG to solve it
Megaboy12346/complex-RAG-guide
Build a robust, production-ready RAG system with effective data preparation, anonymization, and...