zhuyongxin 9cf162482d refactor(rag): extract retrieval and ingest to py-rag service ...

- replace in-process Milvus stack with PyRagClient + PyRagKnowledgeSearchAdapter behind KnowledgeSearchPort (RERANK score passthrough)
- move document ingest to py-rag /documents:ingest; DocumentManagementService keeps MySQL ledger + local files
- sink L0 query understanding to py-rag; drop KnowledgeQueryTransformer, single UNFILTERED_VECTOR attempt
- remove Milvus deps, config classes, dead demo services and obsolete rebuild scripts
- compose/Makefile reduced to MySQL/Redis; add pyrag.* config

2026-09-30 17:03:21 +08:00

..

eval_rag_retrieval.py

feat(rag): close eval pipeline with live snapshots

2026-07-06 21:39:27 +08:00

generate_rag_lookup_snapshots.ps1

feat(harness,rag): dual LLM audit fields, run conclusion, and hybrid quality

2026-07-28 19:43:13 +08:00

prepare_rag_eval_seed.ps1

feat(rag): close eval pipeline with live snapshots

2026-07-06 21:39:27 +08:00

query_mysql.py

feat(harness): add readonly mysql tool

2026-07-21 21:24:42 +08:00

verify-logging.bat

commit

2026-05-31 21:45:14 +08:00