Anthropic introduces Contextual RAG and here are some key points!
Embeddings+BM25 is better than embeddings on their own;
Voyage and Gemini have the best embeddings of the ones we tested;
Passing the top-20 chunks to the model is more effective than just the top-10 or top-5;
Adding context to chunks improves retrieval accuracy a lot;
Reranking is better than no reranking;
All these benefits stack: to maximize performance improvements, we can combine contextual embeddings (from Voyage or Gemini) with contextual BM25, plus a reranking step, and adding the 20 chunks to the prompt.

🔗 Links 🔗

https://www.anthropic.com/news/contex...


❤️ If you want to support the channel ❤️
Support here:
Patreon -   / 1littlecoder  
Ko-Fi - https://ko-fi.com/1littlecoder

🧭 Follow me on 🧭
Twitter -   / 1littlecoder  
Linkedin -   / amrrs