Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
Commits on master
fix(runtime): use selected GPU memory for automatic tiers
57c8e4d Xiaomeng Zhao committed 23 days ago
docs: update changelog for 4.1.0 release notes and API changes
67dc08b myhloli committed 23 days ago
docs: prepare bilingual 4.1 release notes and API guides
9b3bdd9 Xiaomeng Zhao committed 23 days ago
Merge pull request #5673 from totoyang/fix/kit-zip-tempdir
8da059c Xiaomeng Zhao committed 23 days ago
Merge remote-tracking branch 'upstream/dev' into codex/pr-5673-zip-export
b7d2691 myhloli committed 23 days ago
fix(ci): align hardware and tier changes with repository checks
17e885e myhloli committed 23 days ago
feat(gpu): enhance GPU classification and identity matching for improved hardware detection
129d945 myhloli committed 23 days ago
feat(hardware): add hardware detection and info commands for diagnostics
3535fcd myhloli committed 24 days ago
refactor(api): unify tier handling for native documents and update CLI options
4c9f9df myhloli committed 24 days ago
refactor(api): update tier handling to support multiple tiers in API calls
a243103 myhloli committed 24 days ago
Merge pull request #5665 from opendatalab/codex/architecture-lifecycle-refactor
c8028a8 Xiaomeng Zhao committed 26 days ago