https://github.com/patw/docinator

A small service to convert PDF files to Markdown using the Docling library
https://github.com/patw/docinator

docling fastapi llm

Last synced: about 2 months ago
JSON representation

A small service to convert PDF files to Markdown using the Docling library

• Host: GitHub
• URL: https://github.com/patw/docinator
• Owner: patw
• License: mit
• Created: 2025-01-17T20:24:08.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-02-07T12:17:33.000Z (over 1 year ago)
• Last Synced: 2025-05-29T01:39:26.052Z (about 1 year ago)
• Topics: docling, fastapi, llm
• Language: Python
• Homepage:
• Size: 4.88 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Docinator

Provides an API to input PDF files and convert to Markdown text, with some summarization options.  This is useful for chunking PDF for RAG chatbots.

## Local Installation

```

python3 -m venv venv

source venv/bin/activate

pip install -r requirements.txt

```

Copy the model.json.sample to model.json.  In here you can modify the BaseURL to work with any OAI compatible service or use your own local models.

## Running Docinator API

```

uvicorn main:app --host 0.0.0.0 --port 3009 --reload

```

## Accessing API

http://localhost:3009/docs