https://github.com/mrahmed14/retrieve
This project is an information retrieval system using TF-IDF vectorization
https://github.com/mrahmed14/retrieve
Last synced: about 1 month ago
JSON representation
This project is an information retrieval system using TF-IDF vectorization
- Host: GitHub
- URL: https://github.com/mrahmed14/retrieve
- Owner: MrAHMED14
- Created: 2025-03-22T06:28:43.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-04-30T09:51:06.000Z (about 2 months ago)
- Last Synced: 2025-04-30T11:33:03.223Z (about 2 months ago)
- Language: TypeScript
- Homepage:
- Size: 97.7 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## About This Project
This project is a **information retrieval system** that allows users to upload and search documents (PDF & TXT files). It uses **TF-IDF vectorization** for efficient information retrieval. The backend is built with **Flask**, while the frontend is built with **Next.js**.
### Prerequisites
Ensure you have the following installed:
- [**Node.js**](https://nodejs.org/)
- [**Python**](https://www.python.org/)
## API Endpoints
### Upload Files
- **Endpoint:** `POST /upload`
- **Description:** Uploads PDF and TXT files.
- **Usage:**
```bash
curl -X POST -F "[email protected]" http://127.0.0.1:5000/upload
```
### Search Documents
- **Endpoint:** `GET /search?q=`
- **Description:** Searches for a keyword in the uploaded files.
- **Usage:**
```bash
curl -X GET "http://127.0.0.1:5000/search?q=information"
```
## Contributing
Feel free to submit **issues or pull requests** to improve this project!