README.md

metadata

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 with RAG — Ask from File, Web, Image, or Audio

🧠 AI Chatbot with File, Web, OCR & Audio (Gradio + Groq)

A multimodal AI assistant that can answer questions using content from:

• 📄 Uploaded .txt, .pdf, .docx, .csv files
• 🌐 Any website URL (RAG)
• 🖼️ Images (OCR with Tesseract)
• 🎧 Audio files (transcription with Whisper)

---

🚀 Features

• Chat with files (PDF, DOCX, TXT, CSV)
• Extract info from websites
• Perform OCR on images
• Transcribe audio to text
• Keeps file and URL-specific chat history

---

🛠️ Tech Stack

• Gradio UI
• Groq LLaMA 3
• Tesseract OCR
• OpenAI Whisper
• FastAPI backend (if used locally)

---

📦 How to Run Locally

git clone https://github.com/your-username/your-repo.git
cd your-repo
pip install -r requirements.txt
uvicorn main:app --reload     # FastAPI backend
python app.py                 # Gradio frontend