metadata

title: Retrieval AI
emoji: 🖼️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.15.0
app_file: app.py
pinned: false

Retrieval-AI

Overview

Retrieval-AI is a simple image retrieval application using a CLIP model and FAISS indexing. It allows users to search for images based on text queries and provides accessibility features such as dark mode and speech-to-text for visually impaired users.

Features

Text-based Image Search: Users can input a text query to find matching images. Adjustable Results Count: Users can select how many results to display. Example Queries: Predefined queries help users get started. Dark Mode Support: Enhances usability in low-light conditions. Speech-to-Text Input: Allows visually impaired users to speak their queries instead of typing.

Installation

Prerequisites

Python 3.8+ Required dependencies (see requirements.txt if available)

Setup

Clone the repository:

git clone https://github.com/yourusername/retrieval-ai.git cd retrieval-ai
Install dependencies:

pip install -r requirements.txt
Run the application:

python app.py
Open the provided URL in a browser (e.g., http://127.0.0.1:7860).

Usage

Enter a text query or use speech input.
Adjust the number of results (1-10).
View the matched images in the results gallery.

Accessibility Features

Dark Mode: Automatically adapts the UI for better readability in dark environments. Speech-to-Text: Allows users to dictate their search queries for improved accessibility.

License

This project is open-source under the MIT License.

Contact

For any inquiries or contributions, please reach out to Joyce Nhlengetwa at [email protected].