Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonNanoNets/docext

docext

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

71.6/100
2.0KForks: 143
View on GitHubHomepage →
Loading report...

Similar Projects

AdalFlow

76

AdalFlow: The library to build & auto-optimize LLM applications.

Python4.1K

open-webui

94

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Python133.1K

awesome-llm-apps

83

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

Python106.8K

MinerU

93

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Python60.8K
Back to List