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
refactor: clarify task, document and model lifecycle boundaries
afda718 myhloli committed 26 days ago
feat(gradio): cancel remote tasks when conversions are invalidated
ec6c23c myhloli committed 27 days ago
Merge pull request #5662 from opendatalab/codex/ci-pr-gates
ec81e19 Xiaomeng Zhao committed 28 days ago
test(router): wait for upstream job admission before balancing assertions
f1fe642 myhloli committed 28 days ago
refactor(mfr): remove retired HF UniMERNet implementation and tests
70912ee myhloli committed 28 days ago
test(router): wait for upstream job admission before balancing assertions
8e39a19 myhloli committed 28 days ago
refactor(mfr): remove retired HF UniMERNet implementation and tests
2293b50 myhloli committed 28 days ago
refactor(api): simplify task protocol and internalize model output
1399b68 myhloli committed 28 days ago
docs(api): specify Tasks, Files and file_parse response contracts
fb3f81d myhloli committed 28 days ago
refactor(api): unify task file fields and generate optional client IDs
28494e6 myhloli committed 28 days ago