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
feat(tests): add test for PDF download with CJK inline formulas
70a618f myhloli committed 2 months ago
fix(tests): align infer performance log test with info level and add timing.py copyright header
c1ada86 myhloli committed 2 months ago
feat(onnx): unify thread configuration for ONNX sessions with environment variable fallback
2bbaf6e myhloli committed 2 months ago
feat(artifacts): update image naming convention for materialized assets and improve image resolution handling
3103e95 myhloli committed 2 months ago
fix(engine_utils): adjust GPU memory utilization logic for better handling of high VRAM devices
ff6d358 myhloli committed 2 months ago
fix(logging): change log level from info to debug for inference performance logging
9a96c4e myhloli committed 2 months ago
fix(logging): change info logs to debug level for model loading and native table priority
8422b1b myhloli committed 2 months ago
fix(gradio): make _safe_stem idempotent for >120-byte filenames
cbf7c37 myhloli committed 2 months ago
feat(pdf): add PDF CPU gap measurement tool and documentation
99a012b myhloli committed 2 months ago
test(vlm): accept page_vector_geometries kwarg in hybrid_stub retain_vlm_text
23be3d7 myhloli committed 2 months ago