Skip to content

Conversation

@Rishit2000
Copy link
Contributor

  • Store multiple page numbers spanning per chunk in metadata
  • Send all such pages when the API endpoint is hit by UI requests
  • Cleared some AI artefacts from code comments
  • Use absolute path for resolving pdf and markdown files

- Store multiple page numbers spanning per chunk in metadata
- Send all such pages when the API endpoint is hit by UI requests
- Cleared some AI artefacts from code comments
- Use absolute path for resolving pdf and markdown files
@Rishit2000 Rishit2000 changed the title Fix page numbers sent per chunk to UI from backend Fix per-chunk page numbers sent from backend to UI Jan 30, 2026
@jarulraj jarulraj requested review from karvyq and shahmeer99 January 30, 2026 16:21
print("TokenSmith API initialized successfully")
except Exception as exc:
print(f"⚠️ Warning: Could not load artifacts: {exc}")
print(f"Warning: Could not load artifacts: {exc}")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for removing these emojis. Hate when LLMs do that :)

Copy link
Contributor

@shahmeer99 shahmeer99 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Just waiting for the PR before this one to make adjust some of its changes to extraction.py. After that I will merge that one and then approve this one. I think everything here looks good.

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.

3 participants