---
title: AI Chatbot File Web Image Audio
emoji: 🤖
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 5.34.2
app_file: app.py
pinned: false
license: mit
short_description: AI Chatbot using RAG from Files, URLs, Images & Audio
---

# 🧠 AI Chatbot with File, Web, Image & Audio Support (Gradio + Groq)

A multimodal AI assistant powered by Groq's LLaMA 3 that can answer questions using:

- 📄 Uploaded documents (`.txt`, `.pdf`, `.docx`, `.csv`)
- 🌐 Any public website URL (RAG retrieval)
- 🖼️ Images via OCR (Tesseract)
- 🎧 Audio files via transcription (Whisper)

---

## 🚀 Features

- Chat with files (PDF, DOCX, TXT, CSV)
- Question answering from website content
- OCR-based text extraction from images
- Speech-to-text from audio recordings
- Maintains separate history for File & URL chat sessions

---

## 🛠️ Tech Stack

- [Gradio](https://gradio.app) — User Interface
- [FastAPI](https://fastapi.tiangolo.com/) — API Backend
- [Groq API](https://groq.com/) — LLaMA 3 inference
- [Tesseract OCR](https://github.com/tesseract-ocr) — Image text extraction
- [Whisper](https://github.com/openai/whisper) — Audio transcription

---

## 📦 How to Run Locally

```bash
git clone https://github.com/your-username/your-repo.git
cd your-repo

# Install dependencies
pip install -r requirements.txt

# Start FastAPI backend
uvicorn main:app --reload

# Run Gradio frontend
python app.py