All Products
Search

This Product

    Platform For AI:Deploy dedicated CoPaw in 5 minutes using PAI-EAS

    Document Center

    Platform For AI:Deploy dedicated CoPaw in 5 minutes using PAI-EAS

    Last Updated:Mar 23, 2026

    Deploy CoPaw personal agent framework on PAI-EAS and integrate it with PAI-EAS models or Model Studio models to build your AI assistant.

    Deploy an EAS service

    1. 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).

    2. On Inference Service tab, click Deploy Service. In Scenario-based Model Deployment section, click CoPaw Deployment.

    3. Configure key parameters:

      Parameter

      Description

      Service Name

      Example: copaw_demo

      Deployment Method

      Select Image-based Deployment and select Enable Web App checkbox.

      Image Configuration

      Select latest version.

      Resource Configuration

      Select CPU instance type based on your resource requirements. Default: ecs.c7a.large.

      Model Settings

      Select OSS path to persist CoPaw configuration, such as oss://examplebucket/copaw/.

      Deployment

      Select CPU instance type and configure based on your resource requirements. Default: ecs.c7a.large.

      VPC

      Create and configure VPC, vSwitch, and Security Group.

      Note

      CoPaw requires internet access for search and browser functions. Select VPC that already has public network access.

    4. Click Deploy. Wait for service to enter Running state, which indicates successful deployment.

    Configure public network access

    EAS services require Internet NAT Gateway for public internet access. Follow these steps to configure one. For more information, see Use the SNAT feature of an Internet NAT Gateway to access the internet.

    1. Create Internet NAT Gateway and attach EIP

    Go to NAT Gateway - Internet NAT Gateway purchase page.

    • Billing Method: Select pay-as-you-go.

    • Region: Select Region where your EAS service is deployed.

    • Network and Availability Zone: Select VPC configured for your EAS service. This setting cannot be changed after creation.

    • Elastic IP Address (EIP): Select unassociated EIP or purchase new one.

    2. Configure SNAT entry

    Go to Internet NAT Gateway page. Find your Internet NAT Gateway. In Actions column, click Configure SNAT, and then click Create SNAT Entry.

    • SNAT Entry: Select VPC granularity.

    • Select Elastic IP Address: Select configured EIP.

    Start the web UI

    1. In Invoke/Log/Monitoring column, click image button to open Web UI.

      image.png

    2. Configure model. Navigate to Settings > Models to configure Provider. Then, in LLM Configuration section, select provider and model.

      Aliyun Coding Plan

      Go to (international) to subscribe and get your Coding Plan API Key.

      image

      EAS model service

      1. Click Add Provider. For Protocol, select OpenAI-compatible.image

      2. Set URL and API Key. See Get the Endpoint and Token. Append /v1 to endpoint URL.image

      3. Add a model. image

      DashScope

      On DashScope provider card, click Settings and add your Alibaba Cloud Model Studio API Key. See Model List to add more models.

      image

    3. Start conversation with or assign task to your CoPaw personal assistant.

      image.png

    Channel configuration

    CoPaw supports integration with DingTalk, Lark, and other channels. For more information, see Channel Configuration.