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
refactor(parser): drop dead backend_for_tier chain and Hybrid-era locks
dd20bf0 jinzhenj committed 2 months ago
fix(vlm-server): alias model name to registry name instead of file path
f68ed53 jinzhenj committed 2 months ago
feat: update llama server binary handling and improve preload model functions
f095d20 myhloli committed 2 months ago
feat: add support for short spellings of boolean flags in webui command
44d408e myhloli committed 2 months ago
refactor: remove latex delimiters option from API and documentation
58bd959 myhloli committed 2 months ago
feat: polish CLI help copy and add llama-cpp VLM server engine
2d786b1 jinzhenj committed 2 months ago
refactor: remove language option from API server and related components
35a956b myhloli committed 2 months ago
refactor: remove language option from API server and related components
464d473 myhloli committed 2 months ago
fix: ensure consistent height for results area in narrow screen media queries
3263f3c myhloli committed 2 months ago
feat: implement source document preview for HTML files and remove OFD preview
ff349a9 myhloli committed 2 months ago
feat: configure global log level before rendering and parsing operations
e37919c myhloli committed 2 months ago
Merge pull request #5516 from myhloli/fix/release-push-token
23caf85 Xiaomeng Zhao committed 2 months ago
fix: authenticate release version-bump push with RELEASE_TOKEN via checkout credential
85ac82c myhloli committed 2 months ago