e2e: add log for docker test

Author: sangjanai

engine/e2e-test/test_api_docker.py

@@ -18,7 +18,7 @@ def setup_and_teardown(self, request):
     @pytest.mark.parametrize("model_url", repo_branches)
     @pytest.mark.asyncio
     async def test_models_on_cortexso_hub(self, model_url):
-
+        print("Pull model from cortexso hub")
         # Pull model from cortexso hub
         json_body = {
             "model": model_url
@@ -28,6 +28,7 @@ async def test_models_on_cortexso_hub(self, model_url):
 
         await wait_for_websocket_download_success_event(timeout=None)
 
+        print("Check if the model was pulled successfully")
         # Check if the model was pulled successfully
         get_model_response = requests.get(
             f"http://127.0.0.1:3928/v1/models/{model_url}"
@@ -37,16 +38,19 @@ async def test_models_on_cortexso_hub(self, model_url):
             get_model_response.json()["model"] == model_url
         ), f"Unexpected model name for: {model_url}"
 
+        print("Check if the model is available in the list of models")
         # Check if the model is available in the list of models
         response = requests.get("http://localhost:3928/v1/models")
         assert response.status_code == 200
         models = [i["id"] for i in response.json()["data"]]
         assert model_url in models, f"Model not found in list: {model_url}"
 
+        print("Start the model")
         # Start the model
         response = requests.post("http://localhost:3928/v1/models/start", json=json_body)
         assert response.status_code == 200, f"status_code: {response.status_code}"
 
+        print("Send an inference request")
         # Send an inference request
         inference_json_body = {
             "frequency_penalty": 0.2,
@@ -69,6 +73,7 @@ async def test_models_on_cortexso_hub(self, model_url):
         response = requests.post("http://localhost:3928/v1/chat/completions", json=inference_json_body, headers={"Content-Type": "application/json"})
         assert response.status_code == 200, f"status_code: {response.status_code} response: {response.json()}"
 
+        print("Stop the model")
         # Stop the model
         response = requests.post("http://localhost:3928/v1/models/stop", json=json_body)
         assert response.status_code == 200, f"status_code: {response.status_code}"