Generate Tests Using Vision Nova

Generating functional test scenarios for the app screen using our AI based service Vision Nova, through publicly accessible image url using both SDKs and APIs.

Usage 🚀

Refer to Setup Guide for installing dependecies for both Java and Python.

JAVA

There are 2 clients available with the Java SDK: SyncClient and AsyncClient

Java Client Code

# for async client 
import org.qyrus.ai_sdk.Clients.AsyncClient;
AsyncClient client = new AsyncClient(<API_TOKEN>, null);

# for sync client
import org.qyrus.ai_sdk.Clients.SyncClient;
SyncClient client = new SyncClient(<API_TOKEN>, null);

Using SyncClient

Here's an example of utilizing Vision Nova via publicly accessible image url to generate test scenarios with SyncClient.

Java SyncClient Code

private static void createTestVisionNovaScenarios(){

        Dotenv dotenv = Dotenv.load();
        String QYRUS_AI_SDK_API_TOKEN = dotenv.get("QYRUS_AI_SDK_API_TOKEN");

        SyncClient client = new SyncClient(QYRUS_AI_SDK_API_TOKEN, null);
        String image_url = <IMAGE_URL>;

        long startTime = System.currentTimeMillis();
        int numberOfRequests = 2;

        for (int i = 0; i < numberOfRequests; i++) {
            try {
                VisionNovaFunctionalTests.CreateScenariosResponse response = client.vision_nova.functional_tests.create(image_url);
                System.out.println("Creation Status: " + response.isOk());
                System.out.println("Creation Status: " + response.getMessage());
        
                //Show all the scenarios generated
                if (response != null && response.isOk() == true && response.getScenarios() != null) {
                    System.out.println("Creation Status: " + response.getVisionNovaRequestId());

                    List<VisionNovaFunctionalTests.Scenario> scenarios = response.getScenarios();

                    // Loop over the list and print out scenarios
                    for (VisionNovaFunctionalTests.Scenario scenario : scenarios) {
                        System.out.println("Scenario Name: " + scenario.getScenarioName());
                        System.out.println("Scenario Objective: " + scenario.getScenarioObjective());
                        System.out.println("Scenario Description: " + scenario.getScenarioDescription());
                        System.out.println("Scenario Steps: " + scenario.getSteps());
                        
                        System.out.println("--------------------------------------");
                    }

                }
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        long endTime = System.currentTimeMillis();
        System.out.println("Synchronous total time for Vision Nova functional tests" + numberOfRequests + " requests: " + (endTime - startTime) + " ms");
    }

Using AsyncClient

Here's an example of utilizing Vision Nova via the publicly accessible image url to generate test scenarios with AsyncClient.

Java AsyncClient Code

private static void asyncCreateTestVisionNovaScenarios(){
        Dotenv dotenv = Dotenv.load();
        String QYRUS_AI_SDK_API_TOKEN = dotenv.get("QYRUS_AI_SDK_API_TOKEN");

        AsyncClient client = new AsyncClient(QYRUS_AI_SDK_API_TOKEN, null);
        String image_url = "https://s3-us-west-2.amazonaws.com/ctc-qa-ai/ai/demo/public/images/home-loan-screenshot.png";
        int numberOfRequests = 2;

        long startTime = System.currentTimeMillis();

        List<CompletableFuture<AsyncVisionNovaFunctionalTests.CreateScenariosResponse>> futures = new ArrayList<>();

        for (int i = 0; i < numberOfRequests; i++) {

            CompletableFuture<AsyncVisionNovaFunctionalTests.CreateScenariosResponse> responseFuture = client.vision_nova.functional_tests.create(image_url);
        
        
            responseFuture.thenAccept(response -> {
            if (response.isOk()) {
                System.out.println("Creation Status: " + response.isOk());
                System.out.println("Message: " + response.getMessage());
                System.out.println("Creation Status: " + response.getVisionNovaRequestId());

                for (AsyncVisionNovaFunctionalTests.Scenario scenario : response.getScenarios()) {
                    System.out.println("Scenario Name: " + scenario.getScenarioName());
                    System.out.println("Scenario Objective: " + scenario.getScenarioObjective());
                    System.out.println("Scenario Description: " + scenario.getScenarioDescription());
                    System.out.println("Scenario Steps: " + scenario.getSteps());
                    
                    System.out.println("--------------------------------------");
                }

            }
            else {
                System.out.println("Creation failed with message: " + response.getMessage());
            }
        }).exceptionally(ex -> {
            System.out.println("An error occurred: " + ex.getMessage());
            ex.printStackTrace();
            return null;
        });

        // // Keep your program running until all futures are resolved
        // responseFuture.join(); // Block and wait for the future to complete
        futures.add(responseFuture);
        }
        CompletableFuture.allOf(futures.toArray(new CompletableFuture[0])).join();

        long endTime = System.currentTimeMillis();
        System.out.println("Asynchronous total time for Vision Nova Functional Tests" + numberOfRequests + " requests: " + (endTime - startTime) + " ms");
    }

---

PYTHON

There are two clients available with the Python SDK: SyncQyrusAI and AsyncQyrusAI.

Python Client Code

# for sync client
from qyrusai import SyncQyrusAI
client = SyncQyrusAI(api_key=QYRUS_API_TOKEN)

# for async client
from qyrusai import AsyncQyrusAI
client = AsyncQyrusAI(api_key=QYRUS_API_TOKEN)

Using SyncQyrusAI

Here's an example of utilizing Vision Nova via the publicly accessible image url to generate test scenarios with SyncQyrusAI.

Python SyncQyrusAI Code

import os
import json
from qyrusai import SyncQyrusAI

QYRUS_API_TOKEN = os.environ.get("QYRUS_API_TOKEN")

client = SyncQyrusAI(api_key=QYRUS_API_TOKEN)

image_url = "https://cdn.dribbble.com/userupload/12323124/file/original-00fd2fb0c444a812c1cca08bb78cc49f.jpg"

op = client.vision_nova.generate_test.generate(image_url)

# print(json.dumps(op, indent=4))

scenarios = op.get("scenarios")
for scenario in scenarios:
  print(scenario["scenario_name"])
  print(scenario["description"])
  print(scenario["objective"])
  print(scenario["steps"])

Using AsyncQyrusAI

Here's an example of utilizing Vision Nova via the publicly accessible image url to generate test scenarios with AsyncQyrusAI.

Python AsyncQyrusAI Code

import os
import json
import asyncio
from qyrusai import AsyncQyrusAI

QYRUS_API_TOKEN = os.environ.get("QYRUS_API_TOKEN")

client = AsyncQyrusAI(api_key=QYRUS_API_TOKEN)

image_url = "https://cdn.dribbble.com/userupload/12323124/file/original-00fd2fb0c444a812c1cca08bb78cc49f.jpg"

async def main():
    op = await client.vision_nova.generate_test.generate(image_url)
    # print(json.dumps(op, indent=4))
    scenarios = op.get("scenarios")
    for scenario in scenarios:
      print(scenario["scenario_name"])
      print(scenario["description"])
      print(scenario["objective"])
      print(scenario["steps"])


# Run the async function
asyncio.run(main())

---

Rest APIs

• Endpoint: POST {{GATEWAY_URL}}/vision-nova-sdk/v1/api/json-create-tests

• Headers:

  • Authorization: [Your Authorization Token]

  • Custom: [Your Custom Header Value]

• Request Body: { "image_url": "publicly accessible image url" }

• Response: