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

..

__init__.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

audio.py

fix: correct model type mappings and improve system setting persistence (#16501)

2026-07-13 16:42:55 +08:00

book.py

fix(book): preserve PDF coordinate tags in the naive merge branch (#18203)

2026-08-13 17:00:34 +08:00

email.py

feat: add native Dutch language support for BM25 tokenization (#14140)

2026-07-06 23:39:56 +08:00

laws.py

Fix: resolve model_id to model before judge parse method (#17493)

2026-07-29 09:34:52 +08:00

manual.py

feat(MinerU):Add support for MinerU table and image chunk classification (#16703)

2026-08-19 09:52:20 +08:00

naive.py

Fix empty Markdown document parsing (#18503)

2026-08-19 16:33:51 +08:00

one.py

Revert "feat: Go knowledge compiler with scheduler-driven dataset compilation" (#17897)

2026-08-05 21:50:28 +08:00

paper.py

feat(MinerU):Add support for MinerU table and image chunk classification (#16703)

2026-08-19 09:52:20 +08:00

picture.py

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

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

presentation.py

chore(rag/app): remove stray debug print() calls (#17943)

2026-08-08 15:53:16 +08:00

qa.py

Fix QA DOCX table parser dropping cells between repeated text (#17497)

2026-07-29 17:18:54 +08:00

resume.py

docs: document the tenant_id parameter in resume parsing (#18169)

2026-08-12 20:21:26 +08:00

table.py

feat: Gaussdb adaptation (#17703)

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

tag.py

Fix tag CSV parser ignoring the documented TAB delimiter (#17496)

2026-07-29 17:01:07 +08:00