Published on October 15, 2024, the RAG_Techniques repository collects notebooks on retrieval-augmented generation, including reranking, chunking, filtering, and Graph RAG.
The RAG_Techniques GitHub repository offers notebook tutorials for exploring retrieval-augmented generation (RAG) techniques. Topics named in its description include reranking, chunking, filtering, and Graph RAG. The material is presented as a resource for engineers; the description does not report evaluation or performance results.
To consult and verify the material, inspect the notebooks in the original repository and check which techniques each implements; test them with controlled data before drawing conclusions. If you use AI to study or adapt the examples, do not submit sensitive organizational data without authorization, and follow your organization’s data policy.