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(llama): calibrate integrated GPU routing and serialize legacy Intel Vulkan
345f630 Xiaomeng Zhao committed 1 month ago
feat(onnx): add adaptive calibration and Intel WebGPU architecture policy
354566d Xiaomeng Zhao committed 1 month ago
feat(onnx): add Linux WebGPU and compact OCR recognition outputs
a2a4960 Xiaomeng Zhao committed 1 month ago
fix(layout): raise inline formula confidence threshold to 0.45
09b37cc myhloli committed 1 month ago
fix(ocr): skip zero-sized seal crops without misaligning results
1b2be98 myhloli committed 1 month ago
feat: update issue template and sync published release version
7769867 myhloli committed 1 month ago
chore(deps): bump mineru-llama-cpp and mineru-vl-utils minimum versions
a87030c myhloli committed 1 month ago
feat(doclib): add paginated filename search and unified page selectors
aca9b06 myhloli committed 1 month ago