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
Merge pull request #5749 from crunz-ailab/fix/doclib-read-continuation
261f1fe Xiaomeng Zhao committed 9 days ago
test(doclib): cover default-budget continuation and clarify cursor contract
f19a1c2 myhloli committed 9 days ago
Merge remote-tracking branch 'upstream/dev' into codex/pr-5749-continuation
6882a69 myhloli committed 9 days ago
fix(doclib): align Windows managed port probes with server binding
b08e955 myhloli committed 9 days ago
fix(doclib): bound managed parse-server recovery and clean up processes
9290a15 myhloli committed 9 days ago
fix(doclib): preserve content across truncated locator reads
fa6dee7 crunz-ailab committed 10 days ago
Merge pull request #5743 from Ymmcc/fix/doclib-literal-fts-queries
341d192 Xiaomeng Zhao committed 10 days ago
fix(onnx): gate automatic discrete GPU selection on total memory
32bfd78 myhloli committed 11 days ago
fix(model): persist file manifests and pin ModelScope snapshots
74dd405 myhloli committed 11 days ago
fix(model): exclude directories from ModelScope file manifests
d98ed13 myhloli committed 11 days ago
test(webui): ignore looping stars when settling tier controls
8646e18 my hloli committed 11 days ago