https://github.com/neka-nat/mineru-api

Parse PDF API server
https://github.com/neka-nat/mineru-api

docx markdown pdf xlsx

Last synced: 21 days ago
JSON representation

Parse PDF API server

• Host: GitHub
• URL: https://github.com/neka-nat/mineru-api
• Owner: neka-nat
• License: agpl-3.0
• Created: 2021-04-26T12:15:53.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2024-11-16T03:38:43.000Z (about 1 month ago)
• Last Synced: 2024-11-26T22:56:46.510Z (26 days ago)
• Topics: docx, markdown, pdf, xlsx
• Language: Python
• Homepage:
• Size: 7.16 MB
• Stars: 10
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# MinerU API Server

API server for [MinerU](https://github.com/opendatalab/MinerU).

## Quick Start

```bash

git clone https://github.com/neka-nat/mineru-api.git

cd mineru-api

docker compose up

# GPU

docker compose up -f docker-compose.gpu.yml

```

## Request parsing

Use curl.

```bash

curl -X PUT http://localhost:3000/api/parse -F "file=@/path/to/file.pdf"

```

Or access `http://localhost:3000/docs` in your browser.

### Demo movie (x16)

![demo16](demo16.gif)

## ToDo

- [ ] Download images

- [x] Use GPU

- [ ] Utility for deploying to public cloud