wangxiaolei 45911ab0af feat: using charset_normalizer instead of chardet (#29022)

2025-12-05 11:19:19 +08:00

..

blob

…

entity

use model_validate (#26182)

2025-10-10 17:30:13 +09:00

firecrawl

refactor: Update Firecrawl to use v2 API (#24734)

2025-10-15 10:48:54 +08:00

unstructured

refactor: use dynamic max characters for chunking in extractors (#26782)

2025-10-13 10:22:59 +08:00

watercrawl

change all to httpx (#26119)

2025-10-10 23:41:16 +08:00

csv_extractor.py

…

excel_extractor.py

…

extract_processor.py

remove .value (#26633)

2025-10-11 09:08:29 +08:00

extractor_base.py

…

helpers.py

feat: using charset_normalizer instead of chardet (#29022)

2025-12-05 11:19:19 +08:00

html_extractor.py

…

jina_reader_extractor.py

feat: knowledge pipeline (#25360)

2025-09-18 12:49:10 +08:00

markdown_extractor.py

…

notion_extractor.py

change all to httpx (#26119)

2025-10-10 23:41:16 +08:00

pdf_extractor.py

…

text_extractor.py

…

word_extractor.py

Fix: Correctly handle merged cells in DOCX tables to prevent content duplication and loss (#27871)

2025-11-13 15:56:24 +08:00