mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-29 16:05:35 +08:00
51bc41b2e8
### What problem does this PR solve? Improve image table context. Current strategy in attach_media_context: - Order by position when possible: if any chunk has page/position info, sort by (page, top, left), otherwise keep original order. - Apply only to media chunks: images use image_context_size, tables use table_context_size. - Primary matching: on the same page, choose a text chunk whose vertical span overlaps the media, then pick the one with the closest vertical midpoint. - Fallback matching: if no overlap on that page, choose the nearest text chunk on the same page (page-head uses the next text; page-tail uses the previous text). - Context extraction: inside the chosen text chunk, find a mid-sentence boundary near the text midpoint, then take context_size tokens split before/after (total budget). - No multi-chunk stitching: context comes from a single text chunk to avoid mixing unrelated segments. ### Type of change - [x] Refactoring --------- Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>