Linux

If you are using a cloud server, you need to install Linux remote connection tools for deployment.

Installing Linux remote connection tools

Ⅰ. Basic Requirements

1.CPU: Minimum 4 cores, recommended 8 cores

2.Memory: > 16GB

3.GPU(Single Card）: Nvidia RTX 3060/Nvidia RTX 3080/Nvidia RTX 3090

4.Hard Drive >512GB

5.Internet: 5-10M

6.Public Address: Mandatory

6.1 Static Public IP You need to have a static public IP to ensure that the inference node can be reliably accessed by external networks.

6.2 Public IP Direct Connection to Inference Node The public IP should be directly bound to the network interface of the inference node so that external networks can directly access the inference node via this IP. If there are routers or other networking devices in the network, you must have the capability to configure these devices. Port forwarding should be set up to accurately forward external access requests to the corresponding port of the inference node, ensuring that the inference interface can provide normal services externally.

By meeting the above conditions, you can ensure the stability and availability of the inference node's access and services.

Ⅱ. Install Docker

Prerequisites

• Ensure your system supports Docker and has the NVIDIA driver installed to support GPU.

1.Update Package Index

Copy code

sudo apt-get update

2.Install Required Packages

Copy code

sudo apt-get install apt-transport-https ca-certificates curl software-properties-common

3.Add Docker’s Official GPG Key

Copy code

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -

4.Set Up Docker Stable Repository

Copy code

sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"

5.Update Package Index Again

Copy code

sudo apt-get update

6.Install Docker CE

Copy code

sudo apt-get install docker-ce

7.Install NVIDIA Container Toolkit

Copy code

sudo curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)

Copy code

sudo curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

Copy code

sudo apt-get update

Copy code

sudo apt-get install -y nvidia-docker2

Copy code

sudo systemctl restart docker

8.Start and Enable Docker Service

Copy code

sudo systemctl start docker

Copy code

sudo systemctl enable docker

9.Verify Installation

Copy code

docker --version

Ⅲ. Install Docker Compose

Download the latest version of Docker Compose:

Copy code

sudo curl -L "https://github.com/docker/compose/releases/download/v2.5.0/docker-compose-$(uname -s)-$(uname -m)" -o /usr/local/bin/docker-compose

Add executable permissions to the Docker Compose binary：

Copy code

sudo chmod +x /usr/local/bin/docker-compose

Test if the installation was successful：

Copy code

docker-compose --version

Ⅳ. Install Git

1.Update the existing package lists.

Copy code

sudo apt-get update

2.Install Git：

Copy code

sudo apt-get install git

2.After installation, run the following command to verify if the installation was successful:

Copy code

git --version

Ⅴ. Deploy the HyperAGI Inference System

Step 1: Clone the Code Repository

1.Open the terminal or command prompt, and clone the HyperAGI-setup-script GitHub repository:

Copy code

git clone https://github.com/xfangs/hyperAGI-setup-script.git

2.Navigate to the cloned code repository directory:

Copy code

cd hyperAGI-setup-script

Step 2: Configure Environment Variables

1.Within the cloned code repository, there is a .env file where you can configure environment variables. Open the .env file using a text editor:

Copy code

nano .env

2.Configure the variables PUBLIC_IP and WALLET_ADDRESS

PUBLIC_IP: This is the public IP address of your server. You can find it by running the following command in the terminal:

Copy code

curl ifconfig.me

Copy and paste the outputted IP address into the PUBLIC_IP variable in the .env file.

WALLET_ADDRESS: This is your wallet address used for receiving and managing funds related to AI inference. Ensure you use a valid Ethereum wallet address and paste it into the WALLET_ADDRESS variable in the .env file.

Modify environment variables as necessary.

3.After making modifications, perform the following actions:

Ctrl + O (to write changes).

Ctrl + Enter (to save).

Ctrl + X (to exit).

Step 3: Pull Docker Images

Ensure you have the latest Docker images by running the following command:

Copy code

docker-compose pull

Step 4: Start the Service

Run the following command to start the Docker Compose service:

Copy code

docker-compose up -d

The -d flag indicates that the service will run in the background.

Step 5: Verify Deployment

You can verify if the service is running correctly by checking the status of the containers:

Copy code

docker-compose ps

You should see a list of running containers. Ensure that the status of all services is 'running'.

Access to ports 5200 TCP and 5100 TCP needs to be enabled.

Additional Notes

For further troubleshooting, check the logs for additional information if encountering any issues:

Copy code

docker-compose logs

For more advanced configurations, please refer to the docker-compose.yml file in the code repository.

Conclusion

By following these steps, you should be able to deploy and run the complete HyperAGI inference system using Docker Compose. If you encounter any issues or need further assistance, please refer to the documentation or seek support from the community.