Merge branch 'main' into litellm_bedrock_command_r_support

litellm/tests/test_completion.py

@@ -1305,7 +1305,7 @@ def test_hf_classifier_task():
 
 ########################### End of Hugging Face Tests ##############################################
 # def test_completion_hf_api():
-# # failing on circle ci commenting out
+# # failing on circle-ci commenting out
 #     try:
 #         user_message = "write some code to find the sum of two numbers"
 #         messages = [{ "content": user_message,"role": "user"}]
@@ -3300,6 +3300,25 @@ def test_completion_watsonx():
         pytest.fail(f"Error occurred: {e}")
 
 
+def test_completion_stream_watsonx():
+    litellm.set_verbose = True
+    model_name = "watsonx/ibm/granite-13b-chat-v2"
+    try:
+        response = completion(
+            model=model_name,
+            messages=messages,
+            stop=["stop"],
+            max_tokens=20,
+            stream=True,
+        )
+        for chunk in response:
+            print(chunk)
+    except litellm.APIError as e:
+        pass
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 @pytest.mark.parametrize(
     "provider, model, project, region_name, token",
     [
@@ -3364,6 +3383,26 @@ async def test_acompletion_watsonx():
         pytest.fail(f"Error occurred: {e}")
 
 
+@pytest.mark.asyncio
+async def test_acompletion_stream_watsonx():
+    litellm.set_verbose = True
+    model_name = "watsonx/ibm/granite-13b-chat-v2"
+    print("testing watsonx")
+    try:
+        response = await litellm.acompletion(
+            model=model_name,
+            messages=messages,
+            temperature=0.2,
+            max_tokens=80,
+            stream=True,
+        )
+        # Add any assertions here to check the response
+        async for chunk in response:
+            print(chunk)
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 # test_completion_palm_stream()
 
 # test_completion_deep_infra()