Skip to content

Conversation

@ian-katsuno
Copy link
Member

  • paralelized extract_tooll_direct call in process_chat response because it was taking too long we were hitting 30s lambda timeout
  • change chat mode from graph_vector_fulltext to just graph_vector
  • change Magic_trek_chatbot to point to new stronger neo4j aura instance (magic-trek-rag-grade-6)

@ian-katsuno ian-katsuno merged commit 038efe8 into magic-trek-v0 Apr 1, 2025
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