React + Vite

Currently, two official plugins are available:

• @vitejs/plugin-react uses Babel for Fast Refresh
• @vitejs/plugin-react-swc uses SWC for Fast Refresh

• Vision AI - Visual Question Answering Chatbot

Team Name: Rank_Codex
Team Members: Abhishek (Lead), Aishwarya D

---

🚀 Project Overview

Vision AI is a multimodal chatbot that allows users to upload images and ask questions about them. It uses powerful vision-language models (like LLaVA or Gemini) to analyze visual content and provide intelligent responses in real time.

---

🛠️ Tech Stack

• Frontend: React, Tailwind CSS
• Backend/API: FastAPI (or Gemini API Proxy)
• AI Model: Gemini / Hugging Face LLaVA
• Deployment: Vercel (Frontend)

---

⚙️ Setup Instructions

1. Clone the Repository

git clone https://github.com/Aishwarya011k/llava-hack.git
cd llava-hack

2. Install Frontend Dependencies

cd frontend
npm install

3. Run the Frontend

npm run dev

Make sure you have Node.js and npm installed.

---

📷 How to Use

1. Open the app in your browser.
2. Upload an image (e.g., diagram, chart, screenshot).
3. Ask a question related to the image.
4. Get an intelligent answer from the AI.

---

📦 Dependencies

• Node.js
• Python 3.8+
• OpenAI/Google API key (if using hosted models)
• Hugging Face Transformers (if running locally)

---

💡 Example Use Cases

• Education: "What does this circuit diagram show?"
• Accessibility: "Describe the photo for me."
• Business: "What trend does this chart illustrate?"

---

📩 Contact

For questions, please reach out to:

• Abhishek - [abhishek346a@gmail.com]
• Aishwarya D - [aishwaryadshetty019@gmail.com]

Expanding the ESLint configuration

If you are developing a production application, we recommend using TypeScript with type-aware lint rules enabled. Check out the TS template for information on how to integrate TypeScript and typescript-eslint in your project.