https://github.com/bessouat40/photo-gallery-viewer

This project is a photo gallery app 🎨 It leverages a CLIP model for powerful image search based on text keywords. You can easily filter through your images using AI-driven queries!
https://github.com/bessouat40/photo-gallery-viewer

artificial-intelligence data-visualization elasticsearch embeddings image-gallery image-search mvc-architecture offline photo-gallery python

Last synced: 1 day ago
JSON representation

This project is a photo gallery app 🎨 It leverages a CLIP model for powerful image search based on text keywords. You can easily filter through your images using AI-driven queries!

• Host: GitHub
• URL: https://github.com/bessouat40/photo-gallery-viewer
• Owner: Bessouat40
• License: mit
• Created: 2024-05-31T19:37:21.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-11-10T19:36:42.000Z (7 days ago)
• Last Synced: 2024-11-10T20:29:16.696Z (7 days ago)
• Topics: artificial-intelligence, data-visualization, elasticsearch, embeddings, image-gallery, image-search, mvc-architecture, offline, photo-gallery, python
• Language: TypeScript
• Homepage:
• Size: 50.4 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# File Explorer

This project allows you to visualize your images stored inside an Elastic database.

![darkMode](./media/dark.png)

![lightMode](./media/light.png)

## Launch application

- You need to launch frontend :

```bash

npm start

```

- You need to launch backend :

```bash

cd api

python main.py

```

## Requirements

### Database

You need to have an `elasticsearch` database,

### Environment

You need to configure your environment.

First :

```bash

mv .env.example .env

```

Then fill .env file with your informations.

`DATA_FOLDER` is the folder where you'll store all your images.

### IP Adress

Finally, you need to enter your frontend adress into `src/config.json`.

```bash

mv src/config_template.json src/config.json

```

```json

{

  "backendURL": // ex : http://localhost:8000

}

```

## TODO

- [x] Add CLIP use for image filtering,

- [x] Change elasticsearch database : store only embeddings + ref to local images and not encoded images,

- [x] Change CLIP filter to match new software structure,

- [x] Improve frontend,

- [ ] Work on an easy launching method,

- [ ] Add paging,

- [ ] Application conteneurisation,

- [ ] Allow CLIP use when offline