|
--- |
|
license: mit |
|
title: Omniparser-api |
|
sdk: docker |
|
emoji: 😻 |
|
colorFrom: red |
|
colorTo: yellow |
|
--- |
|
|
|
# Omniparser API |
|
|
|
The Omniparser API is a versatile and efficient tool designed to parse, process, and analyze various types of documents or datasets using machine learning models. |
|
|
|
## Features |
|
|
|
- Upload and process documents (e.g., images, PDFs). |
|
- Detect objects, text, or patterns within uploaded files. |
|
- Analyze and parse structured or unstructured content. |
|
- Highly configurable thresholds for precision and flexibility. |
|
|
|
## How to Use |
|
|
|
1. **Upload a Document**: Send a file (e.g., an image or PDF) via the `/process/` endpoint. |
|
2. **Adjust Thresholds**: Configure `box_threshold` and `iou_threshold` for desired accuracy. |
|
3. **Receive Results**: Get a JSON response with parsed content and processed outputs. |
|
|
|
## Endpoints |
|
|
|
- **`GET /`**: Welcome page for the API. |
|
- **`POST /process/`**: Upload and process a document with configurable thresholds. |
|
|
|
## Installation |
|
|
|
1. Clone the repository: |
|
```bash |
|
git clone https://github.com/your-username/omniparser-api.git |
|
cd omniparser-api |
