Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Feature/issue 25/create chat with repo compoent #32

Conversation

innovation64
Copy link
Collaborator

  • Refactor the code to use JSON as the database.
  • Didn't use llamaindex, instead used the built-in Chroma index.
  • Add code blocks at the end of each query.
  • Directly use md_content content for embedding.
  • LLM tokenization search and global retrieval completed.
  • Vector retrieval uses Chroma's built-in engine.
  • Not suitable for multi-turn conversations; it's too long, and one round typically exceeds 4096 tokens.
  • Add a tree structure summary.
  • No fixed database is established; the program automatically updates upon each restart.
  • Add a log file to track keywords and recall embeddings.

@LOGIC-10 LOGIC-10 merged commit 973bec8 into OpenBMB:chat_with_repo Jan 8, 2024
@Umpire2018 Umpire2018 linked an issue Jan 11, 2024 that may be closed by this pull request
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.

chat with repo workflow issue
2 participants