RadarTopicsBuildersWeeklyReads
Open Source Radar
CatchTheTornado/

text-extract-api

GitHubWebsite

text-extract-api provides a local OCR and document conversion API using EasyOCR, Ollama models, and optional remote marker OCR, with Redis caching and Celery task processing. It supports PDF/Office to Markdown or JSON with PII removal and storage options.

3.2kstars
277forks
47issues
MITlicense
2024since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
PaddlePaddle/
PaddleOCR
▲ 532/wk

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

87k11kPython
PDFMathTranslate/
PDFMathTranslate
▲ 119/wk

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

36k3.2kPython
siyuan-note/
siyuan
▲ 150/wk

A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

46k2.9kTypeScript
NousResearch/
hermes-agent
▲ 3.5k/wk

The agent that grows with you

225k44kPython
Significant-Gravitas/
AutoGPT
▲ 72/wk

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

186k46kPython
huggingface/
transformers
▲ 266/wk

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

163k34kPython
Reviewgenerated from repository data · Aug 5, 2026

What it is

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

How it works

  • API built with FastAPI and uses Celery for asynchronous task processing. Redis is used for caching OCR results.
  • Supports multiple OCR strategies: EasyOCR, minicpm-v, llama_vision, and remote markers via marker-pdf. Ollama models load for second-stage text extraction. Output can be Markdown or JSON.
  • Storage strategies for results, including local filesystem and Google Drive. CLI and API endpoints drive task submission and result retrieval.

Getting started

Prerequisites

  • Download and install Ollama
  • Download and install Docker

Clone and setup

git clone https://github.com/CatchTheTornado/text-extract-api.git
cd text-extract-api

Setup with Makefile

DISABLE_VENV=1 make install

DISABLE_VENV=1 make run

Manual setup

cp .env.localhost.example .env.localhost

python3 -m venv .venv
source .venv/bin/activate
pip install -e .
chmod +x run.sh
run.sh

Running CLI for OCR

python client/cli.py ocr_upload --file examples/example-mri.pdf --ocr_cache

Scaling parallel processing

celery -A text_extract_api.tasks worker --loglevel=info --pool=solo

Recent releases

  • v0.3.0 (2025-04-29): Hotfix - duplicated unify, missing libglib in docker and killing cellery pids; added minicpm-v support.
  • v0.2.0 (2025-01-18): Marker licensing changes, EasyOCR support, license updated to MIT.
  • v0.1.0 (2025-01-15): Initial release with PDF, image, Marker OCR, LLama 3.2-vision OCR, and Ollama-supported models.

Traction

3154 stars, 277 forks, 47 open issues.

Behind the repo

No startup/company link provided in the facts.

Caveats

  • License: MIT
  • Created: 2024-10-23
  • Last push: 2025-12-08
  • Age-related notes not explicitly provided beyond release history.
SharePost on XLinkedIn
All trending reposRevenue-verified startups →