feat: page-aware sources + numbered RAG citations (#2106)#2353
Open
RealBhupesh wants to merge 2 commits intoarc53:mainfrom
Open
feat: page-aware sources + numbered RAG citations (#2106)#2353RealBhupesh wants to merge 2 commits intoarc53:mainfrom
RealBhupesh wants to merge 2 commits intoarc53:mainfrom
Conversation
added 2 commits
April 2, 2026 11:28
) - Docling PDF: per-page segments with page metadata; bulk reader merges segment extra_info - ClassicRAG + rag_prompt_docs: pass page through; build numbered excerpts for prompts - Stream/workflow: use build_numbered_docs_together for template context - Research CitationManager: dedupe by page; references show p. N - Frontend: show page on source cards; optional source/link types - Tests: rag_prompt_docs unit tests; adjust workflow/stream pre_fetch assertions Made-with: Cursor
Made-with: Cursor
|
Someone is attempting to deploy a commit to the Arc53 Team on Vercel. A member of the Team first needs to authorize it. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR adds Perplexity-style numbered citations with page-aware RAG sources.
Changes
pagein each chunk’s metadata.ClassicRAG) forwardspageto the frontend sources payload.[1] p. N <filename>and instructions to cite using[1],[2], etc.source + title + page, and references show(p. N).p. N) alongside each source and existing citation clicks continue to jump to the correct source card.Notes
pagemetadata for older documents.Testing
python -m pytest tests/retriever/test_rag_prompt_docs.py -qp. N[1],[2]style citations that correspond to the correct source entriesFuture work (optional)