VictorECDSA ff5971448b [Fix] naive: force-merge short markdown headers to prevent separate chunks (#15488) ...

## Problem

When uploading `.md` files with `parser=naive` and `delimiter="\n"`,
markdown headers (e.g., `## Quick Travel`) become separate chunks with
very short content (16-18 characters). This causes retrieval issues:
when the header is matched, the corresponding body text is not included
in the chunk.

## Related Issues

Closes #15487

## Checklist

- [x] Code changes are minimal and focused
- [x] Unit tests added (12/12 passed)
- [x] No breaking changes

2026-06-03 10:49:28 +08:00

..

advanced_rag

fix: handle missing 'total' key causing KeyError in deep research retrieval (#13942)

2026-05-09 10:57:51 +08:00

app

[Fix] naive: force-merge short markdown headers to prevent separate chunks (#15488)

2026-06-03 10:49:28 +08:00

flow

fix: restore TitleChunker output for json/chunks upstream formats (#15396)

2026-06-01 17:14:22 +08:00

graphrag

GraphRAG - NER - spacy - fix spacy extraction (#14783)

2026-06-01 13:05:54 +08:00

llm

Feature: Add the new anthropic and voyage models (#15516)

2026-06-02 17:29:18 +08:00

nlp

Fix search vector_similarity_weight (#15108)

2026-05-22 16:05:13 +08:00

prompts

Feat: tenant llm provider (#14595)

2026-05-29 17:39:41 +08:00

res

Feat: Bitbucket connector (#12332)

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

svr

feat(connector): implement Outlook data source connector (issue #15332) (#15333)

2026-05-29 21:52:29 +08:00

utils

fix(rag): id2image parsing for hyphenated storage object keys (#15117) (#15118)

2026-06-02 10:52:51 +08:00

__init__.py

Fix: incorrect async chat streamly output (#11679)

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

benchmark.py

Feat: tenant llm provider (#14595)

2026-05-29 17:39:41 +08:00

raptor.py

feat(raptor): add Psi tree builder with original-space ranking and safe migration (#14679)

2026-05-12 09:42:31 +08:00

settings.py

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

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