Azure-Samples / Azure-Samples/get-started-with-ai-chat
Improve RAG
Open
- Dominant language
- Bicep
- Stars
- 280
- Forks
- 401
- Avg merge
- 3d 14h
- Merged PRs (30d)
- 1
Description
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.
Contributor guide
Assessment
This issue has not been assessed yet.