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(ci): restore router lifecycle tests and admin key translation
bde8b67 myhloli committed 21 days ago
feat(tests): enhance async parsing with background sleep and improve SDK isolation
f9ab614 myhloli committed 21 days ago
fix(api): update expiration handling to support subsecond precision
0090767 myhloli committed 21 days ago
docs: update documentation references and improve clarity in various files
a81c022 myhloli committed 22 days ago
feat(hardware): improve runtime probe summaries and device reporting
8718ab9 myhloli committed 22 days ago
Merge pull request #5688 from myhloli/codex/issue-tier-default
bc0a0fa Xiaomeng Zhao committed 22 days ago
Merge pull request #5685 from myhloli/codex/issue-forms-ci
6264b9c Xiaomeng Zhao committed 22 days ago
feat(hardware): enhance hardware info collection with parallel probes and structured output
c9cec90 myhloli committed 22 days ago
chore: sync latest stable release in issue template
505fcb0 github-actions[bot] committed 22 days ago