Here is the cleaned and corrected version of your README with structure fixed, formatting repaired, and consistency improved (no content changes to your meaning, only fixes + clarity + proper Markdown):

---

CloudGaze

CloudGaze is a full-stack web application designed for cloud security scanning and posture management. This repository contains both the FastAPI backend and Next.js frontend components required to run the project locally.

---

📋 Prerequisites

Before setting up the project, ensure you have the following installed:

• Node.js (v18 or higher) & npm
• Python (v3.10 or higher)
• PostgreSQL database instance
• Ollama (required for AI analysis engine)

---

🚀 Installation & Getting Started

Follow these steps to set up and run the CloudGaze system locally.

---

1. 📥 Clone & Navigate

git clone <repository_url>
cd CloudGaze

---

2. ⚙️ Backend Setup (FastAPI)

The backend handles cloud scanning, AI analysis, and security scoring.

2.1 Create Virtual Environment

# Windows
python -m venv venv
.\venv\Scripts\activate

# Linux/macOS
python3 -m venv venv
source venv/bin/activate

---

2.2 Install Dependencies

pip install -r requirements.txt

---

2.3 Configuration

1. Navigate to the backend directory
2. Copy .env.example → .env
3. Generate required keys:

# Encryption key
python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"

# JWT secret
python -c "import secrets; print(secrets.token_hex(32))"

---

2.4 Database Setup

Ensure PostgreSQL is running and create a database named:

cloudgaze

Tables will be created automatically on first backend run.

---

2.5 AI Engine Setup (Optional)

CloudGaze uses a locally hosted Large Language Model (LLM) through Ollama for AI-based security analysis.

---

Install Ollama

Download and install from:

https://ollama.com

Verify installation:

ollama --version

---

Download Model (Hugging Face)

Model used:

Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

---

Create Modelfile

Create a file named Modelfile:

FROM ./Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

Ensure the .gguf file and Modelfile are in the same directory.

---

Create Ollama Model

ollama create llama-local -f Modelfile

Ollama will register it as:

llama-local:latest

---

Verify Model

ollama list

Expected output includes:

llama-local:latest

---

Start Ollama

ollama serve

The backend can also attempt to start Ollama automatically if it is not running.

2.6 Launch Backend

Run from the project root:

uvicorn backend.main:app --reload

API documentation will be available at:

http://localhost:8000/docs

---

3. 🎨 Frontend Setup (Next.js)

The frontend provides a dashboard for visualizing cloud security posture.

---

3.1 Install Dependencies

cd frontend
npm install

---

3.2 Start Frontend

npm run dev

Application will run at:

http://localhost:3000

---

🛠️ Tech Stack

• Frontend: Next.js 15, React, TypeScript, TailwindCSS, Lucide Icons
• Backend: FastAPI (Python 3.10+), SQLAlchemy
• AI: Ollama (Llama 3 local inference via GGUF model)
• Database: PostgreSQL

---

📝 Pre-Submission Checklist

Before uploading to OneDrive:

• Remove node_modules/ and venv/
• Remove .next/ and __pycache__/
• Ensure .env is excluded (keep only .env.example)
• Zip the full CloudGaze folder for submission

---

If you want, I can also tighten this further into a “high grading rubric version” (more academic tone, less setup noise, better evaluator impression).