Jin 372048a02b fix: markdown_extractor lost chunks if it starts without a header(#21308) (#21309)

2025-06-21 23:10:00 +08:00

..

cleaner

fix: keep image url (#17430)

2025-04-04 15:55:48 +08:00

data_post_processor

fix: validate reranking model attributes before processing (#11930)

2024-12-21 21:23:12 +08:00

datasource

feat: add support for Matrixone database (#20714)

2025-06-19 10:20:12 +08:00

docstore

Introduce Plugins (#13836)

2025-02-17 17:05:13 +08:00

embedding

chore: bump mypy to 1.16 (#20608)

2025-06-11 01:01:33 +08:00

entities

Refactor/message cycle manage and knowledge retrieval (#20460)

2025-05-30 14:36:44 +08:00

extractor

fix: markdown_extractor lost chunks if it starts without a header(#21308) (#21309)

2025-06-21 23:10:00 +08:00

index_processor

Minor Improvements for File Validation and Configuration Handling #21179 (#21171)

2025-06-18 18:33:28 +08:00

models

Refactor/remove db from cycle manager (#20455)

2025-05-30 04:34:13 +08:00

rerank

fix: fix rerank model runner usage (#19008)

2025-04-29 14:51:21 +08:00

retrieval

Fixes #20748 KnowledgeRetrievalNode return all external documents when reranker disabled even top-k configed (#20762)

2025-06-18 14:35:12 +08:00

splitter

immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957)

2025-04-30 16:07:20 +08:00

__init__.py

…