lanceyq
f2d7479229
feat(memory): add async user metadata extraction pipeline
- Add MetadataExtractor to collect user-related statements post-dedup
and extract profile/behavioral metadata via independent LLM call
- Add Celery task (extract_user_metadata) routed to memory_tasks queue
- Add metadata models (UserMetadata, UserMetadataProfile, etc.)
- Add metadata utility functions (clean, validate, merge with _op support)
- Add Jinja2 prompt template for metadata extraction (zh/en)
- Fix Lucene query parameter naming: rename `q` to `query` across all
Cypher queries, graph_search functions, and callers
- Escape `/` in Lucene queries to prevent TokenMgrError
- Add `speaker` field to ChunkNode and persist it in Neo4j
- Remove unused imports (argparse, os, UUID) in search.py
- Fix unnecessary db context nesting in interest distribution task
2026-04-09 11:01:56 +08:00
..
2026-01-12 15:59:10 +08:00
2026-03-27 16:54:47 +08:00
2026-02-28 18:58:33 +08:00
2026-04-03 18:57:28 +08:00
2026-04-09 11:01:56 +08:00
2026-03-13 14:36:54 +08:00
2026-03-11 10:45:07 +08:00
2026-04-01 15:47:43 +08:00
2026-01-27 14:04:44 +08:00
2026-04-09 11:01:56 +08:00
2026-04-03 18:57:28 +08:00
2026-04-03 18:57:28 +08:00
2026-02-03 15:24:16 +08:00
2026-04-03 11:44:07 +08:00
2026-01-26 11:53:34 +08:00
2026-03-31 09:59:39 +08:00
2026-04-09 11:01:56 +08:00
2026-03-13 14:47:56 +08:00
2026-03-20 19:53:02 +08:00
2025-12-24 20:35:04 +08:00
2026-04-01 18:03:07 +08:00
2026-02-09 21:23:24 +08:00
2026-04-09 11:01:56 +08:00
2026-03-20 19:52:28 +08:00