Pydantic Lod Test

🚀 Self-hosted AI Starter Kit Guide

This guide provides a comprehensive solution for setting up and managing a local AI workflow environment, catering to users with different hardware configurations. It simplifies the process of building and running AI workflows, offering flexibility and efficiency for developers, data scientists, and technology enthusiasts.

🚀 Quick Start

📦 Installation Guide

For Nvidia GPU Users

docker compose --profile gpu-nvidia pull
docker compose create && docker compose --profile gpu-nvidia up

For Mac / Apple Silicon Users

docker compose pull
docker compose create && docker compose up

For Everyone Else

docker compose --profile cpu pull
docker compose create && docker compose --profile cpu up

💻 Usage Examples

Installation Steps

1. Download and Install Docker: Download and install Docker from the official Docker website according to your operating system (Windows, Mac, or Linux).
2. Clone the Starter Kit Repository:

   git clone https://github.com/your-repository.git
   cd your-repository
   

3. Build and Start the Container:
   • For Nvidia GPU users:

     docker compose --profile gpu-nvidia up -d
     

   • For Mac / Apple Silicon users:

     docker compose up -d
     

   • For other users:

     docker compose --profile cpu up -d
     

4. Access the n8n Interface: Open your browser and visit http://localhost:5678 to access the n8n management interface.

Basic Usage

• Create a New Workflow: Click the "New Workflow" button in n8n to start building your AI workflow.
• Add Nodes: Drag and drop the required nodes (such as AI agents, data sources, etc.) from the left node library onto the canvas.
• Connect Nodes: Connect the nodes by dragging with the mouse to define the data flow direction.
• Set Configurations: Configure the necessary parameters for each node, such as API keys, input fields, etc.
• Run the Workflow: Click the "Run" button to test if your workflow is working properly.

Advanced Usage

1. Use Shared Folders:

   • The starter kit creates a shared folder in the same directory, with the default path /data/shared. You can access the local file system within the n8n container through this path.
   • Related nodes include:
     • Read/Write Files
     • Local File Trigger
     • Execute Command

2. Configure GPU Support:

   • If you are using an Nvidia graphics card, ensure that Docker is correctly configured to use GPU acceleration. You can add the following configuration to the docker-compose.yml file:

     services:
       n8n:
         ...
         deploy:
           resources:
             limits:
               nvidia.com/gpu: 1
     

3. Adjust Performance Parameters:

   • Based on your hardware configuration, appropriately increase the memory and CPU quotas. For example, set the following in docker-compose.yml:

     services:
       n8n:
         ...
         resources:
           limits:
             cpus: '2'
             memory: 4G
     

Upgrade Instructions

1. Stop the Current Container:

   docker compose down
   

2. Pull the Latest Image:
   • For Nvidia GPU users:

     docker compose --profile gpu-nvidia pull
     

   • For Mac / Apple Silicon users:

     docker compose pull
     

   • For other users:

     docker compose --profile cpu pull
     

3. Restart the Container:

   docker compose up -d
   

Tutorials and Resources

• Official Documentation: n8n Official Documentation
• Video Tutorials: n8n Getting Started Guide
• Community Support: Join the n8n User Forum to exchange experiences with users worldwide.

By following the steps above, you can easily set up and run a powerful local AI workflow environment. Whether you are a developer, data scientist, or technology enthusiast, this kit provides you with flexible and efficient tool support.