Commit graph

11 commits

Author SHA1 Message Date
clssck
48c7732edc feat: add automatic entity resolution with 3-layer matching
Implement automatic entity resolution to prevent duplicate nodes in the
knowledge graph. The system uses a 3-layer approach:

1. Case-insensitive exact matching (free, instant)
2. Fuzzy string matching >85% threshold (free, instant)
3. Vector similarity + LLM verification (for acronyms/synonyms)

Key features:
- Pre-resolution phase prevents race conditions in parallel processing
- Numeric suffix detection blocks false matches (IL-4 ≠ IL-13)
- PostgreSQL alias cache for fast lookups on subsequent ingestion
- Configurable thresholds via environment variables

Bug fixes included:
- Fix fuzzy matching false positives for numbered entities
- Fix alias cache not being populated (missing db parameter)
- Skip entity_aliases table from generic id index creation

New files:
- lightrag/entity_resolution/ - Core resolution module
- tests/test_entity_resolution/ - Unit tests
- docker/postgres-age-vector/ - Custom PG image with pgvector + AGE
- docker-compose.test.yml - Integration test environment

Configuration (env.example):
- ENTITY_RESOLUTION_ENABLED=true
- ENTITY_RESOLUTION_FUZZY_THRESHOLD=0.85
- ENTITY_RESOLUTION_VECTOR_THRESHOLD=0.5
- ENTITY_RESOLUTION_MAX_CANDIDATES=3
2025-11-27 15:35:02 +01:00
yangdx
47485b130d refac(ui): Show rerank binding info on status card
- Remove separate ENABLE_RERANK flag in favor of rerank_binding="null"
- Change default rerank binding from "cohere" to "null" (disabled)
- Update UI to display both rerank binding and model information
2025-08-23 02:04:14 +08:00
yangdx
84b09aa5da feat: add threshold status line to StatusCard with i18n support
- Add cosine_threshold, min_rerank_score, related_chunk_number to LightragStatus type
2025-07-28 02:51:36 +08:00
yangdx
5aceca0052 feat(webui): enhance status card with new health endpoint data
- Update StatusCard to display consolidated server info with parallel insert limits and summary settings
- Merge LLM and embedding configurations with async parameters for cleaner display
- Add new status fields to TypeScript interface (summary_language, max_parallel_insert, etc.)
2025-07-28 02:19:27 +08:00
yangdx
465757aa6a Increase status card label width and dialog size 2025-07-13 01:14:12 +08:00
yangdx
ab561196ff Feat: Added reranker config and lock status to status card of WebUI 2025-07-13 00:41:54 +08:00
yangdx
db22cad2c8 feat: add workspace and MAX_GRAPH_NODES to /health endpoint and webui 2025-07-07 01:39:48 +08:00
yangdx
74d015fdba Add description to status dialog 2025-04-07 04:13:40 +08:00
yangdx
c3934ccccb Fix linting 2025-04-04 04:46:40 +08:00
yangdx
9c81963908 Optimize server setting dialogue 2025-04-04 04:35:57 +08:00
yangdx
f8b3f1ee48 Refactor API key alert and remove message alert component
- Move StatusIndicator to status directory
- Remove obsolete MessageAlert component
- Enhance ApiKeyAlert with open state control
- Improve health check logic with alert state
- Add error message display in ApiKeyAlert
2025-03-24 17:00:15 +08:00