Skip to content

Conversation

@Rishit2000
Copy link
Contributor

  • Allow contextualization of chunks before indexing (see: ref).
  • Add a re-ranking module that supports cross-encoder model for now.
  • Add a query transformation module that supports strategies like HyDE (ref), multi-query transform and query decomposition using LLM calls.
  • Implement paragraph-level chunking.

@Rishit2000 Rishit2000 requested a review from jarulraj September 12, 2025 06:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants