Platform For AI:Call a service over a VPC direct connection

SDK for Python

To use the official SDK for Python to call a service, perform the following steps:

1. Run the following code to install the SDK:

   pip install -U eas-prediction --user

   For information about how to use the EAS SDK for Python, see SDK for Python.

2. Compile a call program.

   In the following example, a program that uses strings as input and output is used. For information about sample programs that use other input and output formats, such as TensorFlow or PyTorch tensors, see SDK for Python.

   #!/usr/bin/env python
   from eas_prediction import PredictClient
   from eas_prediction import StringRequest
   from eas_prediction import TFRequest
   from eas_prediction import ENDPOINT_TYPE_DIRECT
   if __name__ == '__main__':
       client = PredictClient('http://pai-eas-vpc.cn-shanghai.aliyuncs.com', 'mnist_saved_model_example')
       # Replace the value with the service token. Find the service that you want to access on the EAS page and click Invocation Method in the Service Type column to obtain the token. 
       client.set_token('M2FhNjJlZDBmMzBmMzE4NjFiNzZhMmUxY2IxZjkyMDczNzAzYjFi****')
       client.set_endpoint_type(ENDPOINT_TYPE_DIRECT)  # Specifies to access the service over a VPC direct connection. 
       client.init()
       # request = StringRequest('[{}]')
       req = TFRequest('predict_images')
       req.add_feed('images', [1, 784], TFRequest.DT_FLOAT, [1] * 784)
       for x in range(0, 1000000):
           resp = client.predict(req)
           print(resp)
   

   The client = PredictClient() function has the following input parameters: endpoint and service_name. The endpoint parameter specifies the endpoint that is used to access the service, and the service_name parameter specifies the service name. The endpoint is associated with the region in the following format: pai-eas-vpc.{RegionId}.aliyuncs.com. For example, the VPC direct connection endpoint in the China (Shanghai) region is pai-eas-vpc.cn-shanghai.aliyuncs.com.

SDK for Java

To call a service by using the official SDK for Java, perform the following steps:

1. Run the following code to add dependencies. To view the latest version of the EAS SDK, go to MVN Repository.

   <dependency>
     <groupId>com.aliyun.openservices.eas</groupId>
     <artifactId>eas-sdk</artifactId>
     <version>2.0.13</version>
   </dependency>

   For information about how to use the EAS SDK for Java, see SDK for Java.

2. Compile a call program.

   import com.aliyun.openservices.eas.predict.http.PredictClient;
   import com.aliyun.openservices.eas.predict.http.HttpConfig;
   
   public class TestString {
       public static void main(String[] args) throws Exception {
           // To ensure that the client object is shared as expected, create and initialize the client object when you start the service instead of creating a client object for each request. 
           PredictClient client = new PredictClient(new HttpConfig());
           // Replace the value with the service token. Find the service that you want to access on the EAS page and click Invocation Method in the Service Type column to obtain the token. 
           client.setToken("YWFlMDYyZDNmNTc3M2I3MzMwYmY0MmYwM2Y2MTYxMTY4NzBkNzdj****");
           // Use the setDirectEndpoint method for VPC direct connections and specify the endpoint in the following format: pai-eas-vpc.{region_id}.aliyuncs.com. For example, the VPC direct connection endpoint in the China (Shanghai) region is pai-eas-vpc.cn-shanghai.aliyuncs.com. 
           client.setDirectEndpoint("pai-eas-vpc.cn-shanghai.aliyuncs.com");
           // Replace the value with the name of the service. 
           client.setModelName("scorecard_pmml_example");
   
           // Define the input strings. 
           String request = "[{\"money_credit\": 3000000}, {\"money_credit\": 10000}]";
           System.out.println(request);
   
           // Obtain the output strings from EAS. 
           try {
               String response = client.predict(request);
               System.out.println(response);
           } catch (Exception e) {
               e.printStackTrace();
           }
   
           // Close the client. 
           client.shutdown();
           return;
       }
   }

SDK for Go

You do not need to install the EAS SDK for Go. The SDK is automatically downloaded from GitHub by the package manager of the Go language during code compilation. For information about how to use the EAS SDK for Go, see SDK for Go.

The following sample code provides an example on how to use the SDK for Go to call a service:

package main

import (
        "fmt"
        "github.com/pai-eas/eas-golang-sdk/eas"
)

func main() {
    // Specify the endpoint in the following format: pai-eas-vpc.{region_id}.aliyuncs.com. For example, the VPC direct connection endpoint in the China (Shanghai) region is pai-eas-vpc.cn-shanghai.aliyuncs.com. Replace the values with the region in which the service is deployed and the name of the service. 
    client := eas.NewPredictClient("pai-eas-vpc.cn-shanghai.aliyuncs.com", "scorecard_pmml_example")
    // Replace the value with the service token. Find the service that you want to access on the EAS page and click Invocation Method in the Service Type column to obtain the token. 
    client.SetToken("YWFlMDYyZDNmNTc3M2I3MzMwYmY0MmYwM2Y2MTYxMTY4NzBkNzdj****")
    client.SetEndpointType(eas.EndpointTypeDirect)
    client.Init()
    req := "[{\"fea1\": 1, \"fea2\": 2}]"
    for i := 0; i < 100; i++ {
        resp, err := client.StringPredict(req)
        if err != nil {
            fmt.Printf("failed to predict: %v\n", err.Error())
        } else {
            fmt.Printf("%v\n", resp)
        }
    }
}