Skip to content

Conversation

@gustavocidornelas
Copy link
Collaborator

Summary

  • Makes sure we're correctly parsing:
    • Citations
    • Reference documents
    • Related questions
  • Extract reference document contents and treat them as contextColumnName.
  • Extract userPseudoId (if present) and treat it as the userIdColumnName.
  • Represent search and rephrase step as nested retriever step for Openlayer.
  • Parse answer_skipped_reasons if present.

@whoseoyster whoseoyster merged commit e5026c7 into main Jan 6, 2026
3 checks passed
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