diff --git a/litellm/tests/test_completion.py b/litellm/tests/test_completion.py index 912b48fa5..424d8d7e4 100644 --- a/litellm/tests/test_completion.py +++ b/litellm/tests/test_completion.py @@ -882,8 +882,7 @@ def test_completion_deep_infra(): print(response.response_ms) except Exception as e: pytest.fail(f"Error occurred: {e}") - - +# test_completion_deep_infra() # Palm tests def test_completion_palm(): # litellm.set_verbose = True diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py index 10aa05536..c41f35e7d 100644 --- a/litellm/tests/test_streaming.py +++ b/litellm/tests/test_streaming.py @@ -426,6 +426,35 @@ def test_completion_palm_stream(): pytest.fail(f"Error occurred: {e}") # test_completion_palm_stream() +# def test_completion_deep_infra_stream(): +# # deep infra currently includes role in the 2nd chunk +# # waiting for them to make a fix on this +# try: +# messages = [ +# {"role": "system", "content": "You are a helpful assistant."}, +# { +# "role": "user", +# "content": "how does a court case get to the Supreme Court?", +# }, +# ] +# print("testing deep infra streaming") +# response = completion( +# model="deepinfra/meta-llama/Llama-2-70b-chat-hf", messages=messages, stream=True, max_tokens=80 +# ) + +# complete_response = "" +# # Add any assertions here to check the response +# for idx, chunk in enumerate(response): +# chunk, finished = streaming_format_tests(idx, chunk) +# if finished: +# break +# complete_response += chunk +# if complete_response.strip() == "": +# raise Exception("Empty response received") +# print(f"completion_response: {complete_response}") +# except Exception as e: +# pytest.fail(f"Error occurred: {e}") +# test_completion_deep_infra_stream() def test_completion_claude_stream_bad_key(): try: