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: skip torch-dependent unit tests via importorskip in torch-free CI
b01b966 myhloli committed 2 months ago
feat: remove `PARSER_BACKENDS` constant from `mineru.parser` exports and update documentation
580a175 myhloli committed 2 months ago
feat: remove `--backend` option from `mineru-kit parse` command and update documentation
2066dc6 myhloli committed 2 months ago
docs: update middle JSON compatibility boundary for 3.x remote
4ce396a jinzhenj committed 2 months ago
refactor: extract shared legacy middle JSON reader to backend postprocess
6f0a27c jinzhenj committed 2 months ago
feat: add example file rendering for supported file types in the Gradio app
73631e0 myhloli committed 2 months ago
feat: add example file rendering for supported file types in the Gradio app
9472eb8 myhloli committed 2 months ago
feat: enhance CSS specificity and visibility for download options and controls
e362305 myhloli committed 2 months ago
feat: update CSS selectors for download menu options to improve visibility and compatibility
6f162b7 myhloli committed 2 months ago
Merge pull request #5501 from opendatalab/release-4.0.0
22f5abb Xiaomeng Zhao committed 2 months ago
feat: implement upload expiration handling and reset restart budget for healthy probes
c8c3ee4 myhloli committed 2 months ago
feat: enforce parse server usage limits and url download size cap (Refs #5501)
3f84fc2 myhloli committed 2 months ago
feat: remove deprecated alpha release workflow and related scripts
32ff574 myhloli committed 2 months ago