diff --git a/litellm/tests/test_streaming.py b/litellm/tests/test_streaming.py index 7a636891be..6c8e25f812 100644 --- a/litellm/tests/test_streaming.py +++ b/litellm/tests/test_streaming.py @@ -204,151 +204,6 @@ def test_completion_cohere_stream_bad_key(): # test_completion_cohere_stream_bad_key() -# def test_completion_nlp_cloud(): -# try: -# messages = [ -# {"role": "system", "content": "You are a helpful assistant."}, -# { -# "role": "user", -# "content": "how does a court case get to the Supreme Court?", -# }, -# ] -# response = completion(model="dolphin", messages=messages, stream=True) -# complete_response = "" -# # Add any assertions here to check the response -# has_finish_reason = False -# for idx, chunk in enumerate(response): -# chunk, finished = streaming_format_tests(idx, chunk) -# has_finish_reason = finished -# complete_response += chunk -# if finished: -# break -# if has_finish_reason is False: -# raise Exception("Finish reason not in final 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_nlp_cloud() - -# def test_completion_nlp_cloud_bad_key(): -# try: -# api_key = "bad-key" -# messages = [ -# {"role": "system", "content": "You are a helpful assistant."}, -# { -# "role": "user", -# "content": "how does a court case get to the Supreme Court?", -# }, -# ] -# response = completion(model="dolphin", messages=messages, stream=True, api_key=api_key) -# complete_response = "" -# # Add any assertions here to check the response -# has_finish_reason = False -# for idx, chunk in enumerate(response): -# chunk, finished = streaming_format_tests(idx, chunk) -# has_finish_reason = finished -# complete_response += chunk -# if finished: -# break -# if has_finish_reason is False: -# raise Exception("Finish reason not in final 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_nlp_cloud_bad_key() - -# def test_completion_hf_stream(): -# try: -# litellm.set_verbose = True -# # messages = [ -# # { -# # "content": "Hello! How are you today?", -# # "role": "user" -# # }, -# # ] -# # response = completion( -# # model="huggingface/mistralai/Mistral-7B-Instruct-v0.1", messages=messages, api_base="https://n9ox93a8sv5ihsow.us-east-1.aws.endpoints.huggingface.cloud", stream=True, max_tokens=1000 -# # ) -# # 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") -# # completion_response_1 = complete_response -# messages = [ -# { -# "content": "Hello! How are you today?", -# "role": "user" -# }, -# { -# "content": "I'm doing well, thank you for asking! I'm excited to be here and help you with any questions or concerns you may have. What can I assist you with today?", -# "role": "assistant" -# }, -# { -# "content": "What is the price of crude oil?", -# "role": "user" -# }, -# ] -# response = completion( -# model="huggingface/mistralai/Mistral-7B-Instruct-v0.1", messages=messages, api_base="https://n9ox93a8sv5ihsow.us-east-1.aws.endpoints.huggingface.cloud", stream=True, max_tokens=1000, n=1 -# ) -# 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_1: {completion_response_1}") -# print(f"completion_response: {complete_response}") -# except InvalidRequestError as e: -# pass -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# test_completion_hf_stream() - -# def test_completion_hf_stream_bad_key(): -# try: -# api_key = "bad-key" -# messages = [ -# { -# "content": "Hello! How are you today?", -# "role": "user" -# }, -# ] -# response = completion( -# model="huggingface/meta-llama/Llama-2-7b-chat-hf", messages=messages, api_base="https://a8l9e3ucxinyl3oj.us-east-1.aws.endpoints.huggingface.cloud", stream=True, max_tokens=1000, api_key=api_key -# ) -# 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 InvalidRequestError as e: -# pass -# except Exception as e: -# pytest.fail(f"Error occurred: {e}") - -# test_completion_hf_stream_bad_key() - def test_completion_azure_stream(): try: litellm.set_verbose = True