To enable Google login, follow these steps:

1. Google Cloud Console:

   • Create a project and enable the Google+ API.
   • Create an OAuth Client ID (Web application type).
   • Add authorized redirect URIs:
     • https://[YOUR_PROJECT_REF].supabase.co/auth/v1/callback
     • http://localhost:3000/auth/callback (for local development)
   • Copy the Client ID and Client Secret.

2. Supabase Dashboard:

   • Navigate to Authentication > Providers.
   • Enable Google.
   • Paste the Client ID and Client Secret from Google.
   • Save changes.

Zola requires Supabase for authentication and storage. To set it up:

1. Create a project at Supabase.
2. Apply the database schema using the provided SQL script.
3. Create storage buckets for chat attachments.
4. Configure authentication providers (e.g., Google OAuth).
5. Add your API keys to .env.local.

To run Zola, ensure your environment meets the following requirements:

• Node.js: 18.x or later
• Package Manager: npm or yarn
• Version Control: Git
• Backend/Auth: A Supabase account (for authentication and storage)
• AI Models: API keys for supported providers (OpenAI, Mistral, etc.) or Ollama for running models locally.

Ollama allows you to run AI models locally. Zola has built-in support for Ollama with automatic model detection, intelligent categorization, and smart tagging. No additional configuration is required for local installations.

### macOS and Linux

```bash
curl -fsSL https://ollama.ai/install.sh | sh

Windows

Download and install from ollama.ai

Docker

docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

To enable the BYOK feature, Zola requires an ENCRYPTION_KEY to securely store user API keys in the database.

Requirements:

• The key must be exactly 32 bytes when base64 decoded.
• Warning: Losing this key will make all existing user API keys unrecoverable. Use the same key across all deployment environments.

Generation Methods:

Node.js

node -e "console.log(require('crypto').randomBytes(32).toString('base64'))"

OpenSSL

openssl rand -base64 32

Python

python -c "import base64, secrets; print(base64.b64encode(secrets.token_bytes(32)).decode())

# Required for BYOK functionality
ENCRYPTION_KEY=your_generated_base64_encryption_key

To run Zola in a local development environment on macOS, Linux, or Windows:

1. Clone the repository.
2. Install dependencies using npm install.
3. Start the development server with npm run dev.

The application will be available at http://localhost:3000.

# Clone the repository
git clone https://github.com/ibelick/zola.git
cd zola

# Install dependencies
npm install

# Run the development server
npm run dev

The CSRF_SECRET protects the application against Cross-Site Request Forgery. Generate a secure random string using one of the following methods and add it to your .env.local file:

Node.js

node -e "console.log(require('crypto').randomBytes(32).toString('hex'))"

OpenSSL

openssl rand -hex 32

Python

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

Vercel Deployment

1. Push code to a Git repository.
2. Import the project into Vercel.
3. Configure environment variables.
4. Deploy using the Vercel CLI.

Self-Hosted Production

Build the application and start the production server manually.

# Deploy via Vercel CLI
npm install -g vercel
vercel

# Self-hosted production build
npm run build
npm start

For a complete local setup including both Zola and Ollama with GPU support, health checks, and automatic model pulling, use the provided docker-compose.ollama.yml file.

To customize which models are pulled automatically, modify the OLLAMA_MODELS environment variable in the compose file.

```bash
# Start both Zola and Ollama services
docker-compose -f docker-compose.ollama.yml up -d

# View logs
docker-compose -f docker-compose.ollama.yml logs -f

# Stop the services
docker-compose -f docker-compose.ollama.yml down

Example customization in docker-compose.ollama.yml

environment:

• OLLAMA_MODELS=llama3.2:3b,gemma2:2b,qwen2.5:3b

Zola requires two specific storage buckets in your Supabase dashboard for handling files:

1. chat-attachments: For user-uploaded files in chats.
2. avatars: For user profile images.

Setup Steps:

1. Go to Storage in your Supabase dashboard.
2. Click New bucket and create chat-attachments.
3. Click New bucket and create avatars.
4. Configure public access permissions for both buckets so they can be accessed by the application.

To allow users to try Zola with limited access before creating an account:

1. Go to your Supabase project dashboard.
2. Navigate to Authentication > Providers.
3. Toggle on Allow anonymous sign-ins.