README.md

---
title: Everycure Ner Pdf
emoji: 🐢
colorFrom: indigo
colorTo: purple
sdk: docker
pinned: false
---

Extract named entities from PDF documents.

## Quick Start

### Installation

```sh
uv venv
UV_PYTHON=3.12 uv pip install -r pyproject.toml
```

### Running Locally

Start the server:

```sh
uv run src/everycure/app.py 
```

### Usage

Process a PDF file (assuming your PDFs are in a `pdfs/` folder):

```sh
curl -X POST -F "file=@pdfs/MECFS systematic review.pdf" http://localhost:8000/api/v1/extract
```

### Remote API

The service is also available remotely:

```sh
curl -X POST -F "file=@pdfs/MECFS systematic review.pdf" https://lucharo-everycure-ner-pdf.hf.space/api/v1/extract 
```

API documentation: <https://lucharo-everycure-ner-pdf.hf.space/docs>

## Development

Run tests:

```sh
uv pip install -e .[dev]
uv run pytest 
```