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>
Install front-end dependencies
npm install
Launch front-end
npm run dev
The following output confirms a successful launch of the system:
Login to RAGFlow web UI
Open your browser and navigate to:
http://localhost:9222 or http://[YOUR_MACHINE_IP]:9222
Replace [YOUR_MACHINE_IP] with your actual machine IP address (e.g., http://192.168.1.49:9222).
Login to RAGFlow web admin UI
Open your browser and navigate to:
http://localhost:9222/admin or http://[YOUR_MACHINE_IP]:9222/admin
Replace [YOUR_MACHINE_IP] with your actual machine IP address (e.g., http://192.168.1.49:9222/admin).
Shutdown front-end
Ctrl + C or
kill -f "umi dev"