Nevar pievienot vairāk kā 25 tēmas Tēmai ir jāsākas ar burtu vai ciparu, tā var saturēt domu zīmes ('-') un var būt līdz 35 simboliem gara.
baonudesifeizhai 1c7404099d
fix: prevent timeout in file encoding detection for large files (#21453)
pirms 4 mēnešiem
..
blob chore: refurbish Python code by applying refurb linter rules (#8296) pirms 1 gada
entity Refactor/remove db from cycle manager (#20455) pirms 5 mēnešiem
firecrawl feat: add search endpoint for Firecrawl Integration (#20521) pirms 4 mēnešiem
unstructured add doc support in knowledge base for unstructured (#17352) pirms 7 mēnešiem
watercrawl Feat(WaterCrawl error handling): add custom exceptions and error handling (#19948) pirms 5 mēnešiem
csv_extractor.py chore(api/core): apply ruff reformatting (#7624) pirms 1 gada
excel_extractor.py py lint (#12102) pirms 10 mēnešiem
extract_processor.py feat: Integrate WaterCrawl.dev as a new knowledge base provider (#16396) pirms 7 mēnešiem
extractor_base.py chore(api/core): apply ruff reformatting (#7624) pirms 1 gada
helpers.py fix: prevent timeout in file encoding detection for large files (#21453) pirms 4 mēnešiem
html_extractor.py feat: mypy for all type check (#10921) pirms 10 mēnešiem
jina_reader_extractor.py feat(website-crawl): add jina reader as additional alternative for website crawling (#8761) pirms 1 gada
markdown_extractor.py fix: markdown_extractor lost chunks if it starts without a header(#21308) (#21309) pirms 4 mēnešiem
notion_extractor.py feat: add pagenation to notion extractor (#20919) pirms 4 mēnešiem
pdf_extractor.py fix: fix the incorrect plaintext file key when saving (#10429) pirms 9 mēnešiem
text_extractor.py fix: prevent timeout in file encoding detection for large files (#21453) pirms 4 mēnešiem
word_extractor.py feat(workflow): domain model for workflow node execution (#19430) pirms 5 mēnešiem