Deploy your dedicated CoPaw on PAI-EAS in 5 minutes - Platform For AI

Deploy the CoPaw personal agent framework on PAI-EAS and integrate it with PAI-EAS custom models or Model Studio models to build your dedicated AI assistant. CoPaw is a local-first, self-hostable framework open-sourced by the AgentScope team. It supports controlling inference costs using a Coding Plan.

Deploy an EAS service

Log on to the PAI console. Select a region on the top of the page. Then, select the desired workspace and click Elastic Algorithm Service (EAS).
On the Inference Service tab, click Deploy Service. In the Scenario-based Model Deployment section, click CoPaw Deployment.

Configure key parameters:

Parameter	Description
Service Name	Enter a name, for example, copaw_demo.
Image Configuration	Select the latest version.
Resource Configuration	Select a CPU instance type and configure it based on your resource requirements. The default value is `ecs.c7a.large`.
Model Settings	Select an OSS path to save the CoPaw configuration, for example, `oss://examplebucket/copaw/`.
VPC	Create and configure a VPC, a vSwitch, and a security group. Note CoPaw requires public internet access to search or use the browser feature. Select a VPC that is already configured for public internet access.

Click Deploy and wait for the service status to change to Running.

Configure public internet access

The EAS service accesses the public internet through an Internet NAT Gateway. For more information, see Internet NAT Gateway.

1. Create Internet NAT Gateway and bind EIP

Go to the NAT Gateway - Internet NAT Gateway purchase page.

Billing Method: Select pay-as-you-go.
Region: Select the region where your EAS service is deployed.
Network and Zone: Select the VPC configured for your EAS service. You cannot change this setting after creation.
EIP: Select an EIP that is not associated with any instance, or purchase a new EIP.

2. Configure an SNAT entry

Go to the Internet NAT Gateway page. Find the Internet NAT Gateway that you created. In the Actions column, click Configure SNAT , and click Create SNAT Entry.

SNAT Entry: Select VPC granularity.
Select EIP: Select the Elastic IP Address (EIP) that you configured.

Start the web UI

In the Invoke/Log/Monitoring column, click the button to open the web UI page.
Configure models. Go to Settings > Models to configure a provider. In the LLM Configuration section, select a provider and a model.
Aliyun coding plan
Go to the Coding Plan page to subscribe to the service and get a dedicated API key.
EAS model service
1. Click Add Provider, and for Protocol, select OpenAI Compatible.
2. Set the URL and API key. For more information, see Get the Endpoint and Token. Append /v1 to the endpoint.
3. Add a model.
DashScope
On the DashScope provider card, click Settings and add your Alibaba Cloud Model Studio API Key. To add more models, see Model List.
Start a conversation with or assign tasks to your CoPaw personal assistant.