Dhruv Diwakirti 86c25068fa fix: keep OCR text when no image2text model is configured (#18012) ...

An image whose OCR text is shorter than the CV LLM threshold produces zero chunks when the tenant has no image2text model configured. The extracted text is discarded.

2026-08-19 21:20:32 +08:00

..

advanced_rag

refa: remove document graph snapshot payload (#18488)

2026-08-19 13:22:37 +08:00

app

fix: keep OCR text when no image2text model is configured (#18012)

2026-08-19 21:20:32 +08:00

flow

Fix ingestion pipeline child delimiter extra newline (#18490)

2026-08-19 13:47:09 +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(llm): disable DeepSeek V4 thinking by default via extra_body (#18241)

2026-08-19 13:47:36 +08:00

nlp

fix: pass Infinity vector similarity weight (#17453)

2026-08-19 20:06:02 +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

feat(chat): add Serply web search provider (#18475)

2026-08-19 18:59:01 +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