Deepseek Ocr Python Packages

pdf-craft

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

doc-page-extractor

Document page extraction tool powered by DeepSeek-OCR.

deocr

A high-performance highly-customizable reverse OCR tool that renders text or huggingface-compatible datasets to images. Dimension, DPI, CSS configurable!

doc-page-extractor-test

doc page extractor can identify text and format in images and return structured data.

inscriber

Local-first CLI that converts academic PDFs into LLM-friendly text-only Markdown using llama.cpp (DeepSeek-OCR + Gemma 4).

oracle-ragcli

RAG CLI for Oracle AI Database, super easy to set up

pdf-craft-cloud

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books. The project has just started.

un-locc

Universal Lossy Optical Context Compression for Vision-Language Models