---
title: AI Multi-Modal Assistant
emoji: 🤖
colorFrom: blue
colorTo: green
sdk: gradio
app_file: app.py
pinned: false
---

# AI Multi-Modal Assistant

## Overview
A web-based AI assistant that can analyze **text** and **images**, providing:
- Text sentiment analysis
- Text summarization
- Keyword extraction
- Image classification with human-readable labels
- Downloadable PDF reports

Built with **Gradio**, **PyTorch**, and **Hugging Face Transformers**.

## Features
- Multi-modal input (text or image)
- Interactive UI with tabs
- PDF report generation
- Deployable online via Hugging Face Spaces

## How to Run Locally

1. Clone the repository
```bash
git clone <repo-url>
cd AI-MultiModal-Assistant
1. Clone the repository:
```bash
git clone <your-github-repo-url>
cd AI-Multi-Modal-Assistant-App