Deployment Guide

This guide explains how to deploy the LangGraph Deployment Kit to production environments.

Deployment Options

There are several ways to deploy the kit:

1. Directly on a server
2. Using Docker
3. Using a cloud platform (AWS, Azure, GCP)

Direct Server Deployment

Prerequisites

• Python 3.11 or higher
• A server with appropriate networking
• API keys for your LLM providers

Steps

1. Clone the repository on your server:

   git clone https://github.com/your-username/langgraph-deployment-kit.git
   cd langgraph-deployment-kit
   

2. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate
   pip install -e .
   

3. Configure environment variables:

   cp .env.example .env
   # Edit .env with production settings
   

4. Start the service (with a process manager like supervisord):

   python src/run_service.py
   

Docker Deployment

Prerequisites

• Docker installed
• Docker Compose (optional, for more complex setups)

Steps

1. Create a Dockerfile in the root directory:

   FROM python:3.12-slim
   
   WORKDIR /app
   
   COPY . .
   
   RUN pip install -e .
   
   EXPOSE 8080
   
   CMD ["python", "src/run_service.py"]
   

2. Build and run the Docker container:

   docker build -t langgraph-deployment-kit .
   docker run -p 8080:8080 --env-file .env langgraph-deployment-kit
   

Cloud Deployment

AWS Elastic Beanstalk

1. Install the AWS EB CLI
2. Configure your application:

   eb init
   

3. Create an environment and deploy:

   eb create
   

Google Cloud Run

1. Install the Google Cloud SDK
2. Build and push your Docker image:

   gcloud builds submit --tag gcr.io/your-project/langgraph-deployment-kit
   

3. Deploy to Cloud Run:

   gcloud run deploy --image gcr.io/your-project/langgraph-deployment-kit --platform managed
   

Production Considerations

Security

• Always set AUTH_SECRET to a strong random string
• Use HTTPS in production environments
• Consider using a reverse proxy like Nginx

Scaling

• For high traffic, consider using a database like PostgreSQL instead of SQLite
• Set up proper monitoring and logging
• Implement rate limiting if needed

Monitoring

• Set up Langfuse for observability
• Consider adding Prometheus metrics
• Set up uptime monitoring

Environment Variables

Key environment variables for production:

• MODE: Set to "deployment" in production
• HOST and PORT: Configure according to your environment
• AUTH_SECRET: A secure authentication key
• DATABASE_TYPE: "postgres" recommended for production
• POSTGRES_*: Configure your PostgreSQL connection