Open-source document parser that converts PDFs, Office files and images into Markdown or JSON for LLM and agent workflows.
82.1K6.8KPythonOtherUpdated yesterday
#layout-analysis
Curated GitHub repositories related to layout-analysis, with AI summaries and key stats.
Open-source document parser that converts PDFs, Office files and images into Markdown or JSON for LLM and agent workflows.
A Python library for document AI that combines layout analysis, OCR, table recognition and token classification into configurable pipelines.