Sevenzuo f1e6b22c4b fix: honor minimum_should_match in GaussDB search (#18456) ...

### Summary

GaussDB DocEngine could return no chunks for conversational queries even
when relevant content was available. `Dealer.search()` supplies
`minimum_should_match` (30%, then 10% on retry), but the GaussDB adapter
discarded it and built a single `plainto_tsquery` from every token. This
effectively required all conversational filler terms to match.

2026-08-18 21:05:49 +08:00

..

advanced_rag

fix(agentic-rag): raise max_parallel_agents for high/ultra to 4, use web search after locate fails repeatedly (#18430)

2026-08-18 19:40:07 +08:00

app

feat: Gaussdb adaptation (#17703)

2026-08-18 09:53:11 +08:00

flow

feat(title-chunker): configurable token-count cap with sentence-boundary re-split (#18455)

2026-08-18 21:03:51 +08:00

graphrag

fix: replace editdistance with rapidfuzz for python 3.13 wheel support (#18132)

2026-08-11 21:44:36 +08:00

llm

fix(model_meta): Base._get_api_key handles JSON-dict api_key for the model-list verify path (#18386)

2026-08-18 20:16:19 +08:00

nlp

Fix parent chunk with extra newline (#18426)

2026-08-18 16:06:30 +08:00

prompts

Refine sufficient check using LLM draft (#18028)

2026-08-10 11:44:47 +08:00

res

Feat: Bitbucket connector (#12332)

2025-12-31 17:18:30 +08:00

svr

Fix task time is incorrect (#18453)

2026-08-18 19:29:25 +08:00

utils

fix: honor minimum_should_match in GaussDB search (#18456)

2026-08-18 21:05:49 +08:00

__init__.py

Fix: incorrect async chat streamly output (#11679)

2025-12-03 11:15:45 +08:00

benchmark.py

refa: resolve tenant model refs consistently (#16744)

2026-07-09 14:02:08 +08:00

settings.py

Move api.settings to common.settings (#11036)

2025-11-06 09:36:38 +08:00