mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-05-23 09:28:06 +08:00
3c4d1da98f
### What problem does this PR solve? The table file parser (CSV/Excel) currently treats all columns identically — every column is both vectorized (embedded in chunk text) and stored as filterable metadata. There's no way for users to control which columns should be searchable by semantic meaning versus which should only be filterable attributes. For example, when ingesting a news articles CSV with columns like title, content, country, category, source, etc., the embedding includes metadata fields like country: Brazil and source: Reuters in the chunk text, which dilutes the semantic quality of the embedding without adding retrieval value. The RDBMS connector (MySQL/PostgreSQL) already supports content_columns / metadata_columns, but this capability was missing for file-based table ingestion. This PR adds column-level control (vectorize / metadata / both) for the table file parser, following RAGFlow's existing patterns. Backward compatible: Datasets without table_column_roles or with table_column_mode: auto behave exactly as before (all columns = both). ### Type of change - [x] New Feature (non-breaking change which adds functionality)
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"