get-started-with-ai-chat icon indicating copy to clipboard operation
get-started-with-ai-chat copied to clipboard
Published 1 month ago • verified publisher icon Azure-Samples

Improve RAG

Open nick863 opened this issue 9 months ago • 1 comments

Currently we use Vector search for RAG and manually do tokenization and vectorization. I have talked to Pamela Fox, and she proposed the next improvements:

  1. Use Hybrid search instead of vector search https://aka.ms/ragrelevance
  2. Add semantic ranker to reduce noise from the vector search
  3. Use Azure AI search built in vectorization
  4. Use Azure AI search built in splitter
  5. Change the documentation accordingly.

nick863 avatar Mar 25 '25 23:03 nick863

How does machine learning differ from traditional programming approaches?

plubala avatar Sep 02 '25 17:09 plubala