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 #5772 from myhloli/codex/release-4.2.2
0621ddb Xiaomeng Zhao committed 6 days ago
Merge master synchronization into the 4.2.2 release preparation
09a42ca myhloli committed 6 days ago
Merge pull request #5770 from myhloli/codex/pr-design-repairs
b030432 Xiaomeng Zhao committed 6 days ago
fix(ci): preserve parse error parameters and align protocol fixtures
9d959fd myhloli committed 6 days ago
fix(runtime): drain LMDeploy probes before releasing the Pipeline
8d465c7 myhloli committed 6 days ago
fix(runtime): require llama.cpp lifecycle contract and verify host integration
2a93ab7 myhloli committed 6 days ago
docs(review): define design-first review and supported acceptance scope
fd5d118 myhloli committed 6 days ago
fix(kit): preserve batch output semantics and classify input failures
7f97abc myhloli committed 6 days ago
fix(runtime): isolate LMDeploy failure and delegate recovery to hosts
359f8c7 myhloli committed 6 days ago
Merge pull request #5759 from myhloli/codex/release-4.2.1
a8c0cf8 Xiaomeng Zhao committed 8 days ago
fix(hardware): preserve Windows DXGI memory in GPU inventory
5c832ae Xiaomeng Zhao committed 8 days ago