Published On Sep 23, 2024
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.
đź”— Links đź”—
https://www.anthropic.com/news/contex...
❤️ If you want to support the channel ❤️
Support here:
Patreon -   / 1littlecoder Â
Ko-Fi - https://ko-fi.com/1littlecoder
🧠Follow me on đź§
Twitter -   / 1littlecoder Â
Linkedin -   / amrrs Â