FestivAI is a multi-agent AI application that generates itineraries to global festivals and countries from users' abstract and concrete prompts.

Watch the complete demo and walkthrough of FestivAI:

• Google Cloud SDK
• Google Cloud Project (GCP) credits
• Python 3.8+
• Node.js

First, configure your Google Cloud environment:

# List available projects
gcloud projects list

# Set the project ID
gcloud config set project festivai-466417

# Enable required APIs
gcloud services enable aiplatform.googleapis.com
gcloud services enable run.googleapis.com
gcloud services enable cloudbuild.googleapis.com
gcloud services enable containerregistry.googleapis.com

Set up authentication for your local environment:

# Authenticate with Google Cloud
gcloud auth login

# Set up application default credentials
gcloud auth application-default login

Create a virtual environment and install dependencies:

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On Windows:
venv\Scripts\activate
# On macOS/Linux:
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

To run the application locally:

# Set environment variables
export GOOGLE_CLOUD_PROJECT=festivai-466417

# Run the application
python main.py

Deploy to Google Cloud Run:

# Build and deploy using Cloud Build
gcloud builds submit --tag gcr.io/festivai-466417/festivai

# Deploy to Cloud Run
gcloud run deploy festivai \
    --image gcr.io/festivai-466417/festivai \
    --platform managed \
    --region us-central1 \
    --allow-unauthenticated

• AI-Powered Content Generation: Create personalized festival greetings using advanced AI models
• Multi-Format Support: Generate content in various formats (text, images, cards)
• Scalable Architecture: Built on Google Cloud for automatic scaling
• Real-time Processing: Fast content generation and delivery
• Customizable Templates: Support for various festival themes and occasions

The application provides RESTful API endpoints for:

• /generate - Generate personalized festival content
• /health - Health check endpoint
• /templates - List available templates
• /customize - Customize existing templates

Key configuration parameters:

• PROJECT_ID: Google Cloud Project ID
• REGION: Deployment region (default: us-central1)
• MODEL_NAME: AI model identifier
• MAX_CONTENT_LENGTH: Maximum content length for generation

Required environment variables:

GOOGLE_CLOUD_PROJECT=festivai-466417
GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-key.json
MODEL_ENDPOINT=your-model-endpoint
API_KEY=your-api-key

The application includes:

• Cloud Monitoring integration for performance metrics
• Cloud Logging for application logs
• Error tracking and alerting
• Custom metrics for content generation statistics

• Python
• React
• TypeScript
• Gemini 2.5 Pro
• Gemma 3
• GCP (Cloud Run)
• NVIDIA L4 GPU