feat: refresh TSLA demo with page-memory parse artifacts - #303
Merged
Conversation
Replace the MinerU chunk demo with a v2 page-view parse so Notebook can cite rendered pages, and teach demo projection to serve page_citation_assets. Co-authored-by: Cursor <cursoragent@cursor.com>
Replace 19 ready demo sources with staging v2 page-view parses so Notebook can cite rendered pages. Five parses failed on staging and the two Micron PDFs could not be fetched past Cloudflare, so those keep the previous chunk artifacts. Co-authored-by: Cursor <cursoragent@cursor.com>
These seven sources were parsed locally but never committed, so the catalog counts pointed at old text/image/table trees. Co-authored-by: Cursor <cursoragent@cursor.com>
GOOG 10-K, Meta earnings call, and SpaceX S-1 had one Root (or speaker) chunk spanning the whole PDF, so citation chips could not land on a page. Expand them to one page chunk per rendered page and point SpaceX examples at p2/p28/p32. Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
apps/api/app/data/demo_documents/tsla-q4-2025) with a staging v2 page-memory parse: 37pagechunks, 18 images, 16 tables, andpage_citation_assets/page PNGs.pagechunk types, servepage_citation_assets, attach demoasset_urls onpage_assets, and resolve citations from chunk summary when OCR text does not contain the original sentence.chunk_count70 → 71 and contract tests to assert page-citation asset upload.Test plan
uv run pytest apps/api/tests/contract/test_demo_documents_contract.py -q(8 passed)pnpm exec vitest run src/integrations/knowhere-demo.test.ts src/domains/chunks/index.test.ts src/domains/demo(29 passed)demo-tsla-q4-2025and open a page chunk in Notebook to verify page PNGs renderMade with Cursor