test: cleanup testing

litellm/llms/openai.py

@@ -265,17 +265,15 @@ class OpenAIChatCompletion(BaseLLM):
                           data: dict, headers: dict, 
                           model_response: ModelResponse): 
         kwargs = locals()
-        if self._aclient_session is None:
-            self._aclient_session = self.create_aclient_session()
-        client = self._aclient_session
         try: 
-            response = await client.post(api_base, json=data, headers=headers, timeout=litellm.request_timeout) 
-            response_json = response.json()
-            if response.status_code != 200:
-                raise OpenAIError(status_code=response.status_code, message=response.text, request=response.request, response=response)
-            
-            ## RESPONSE OBJECT
-            return convert_to_model_response_object(response_object=response_json, model_response_object=model_response)
+            async with httpx.AsyncClient() as client:
+                response = await client.post(api_base, json=data, headers=headers, timeout=litellm.request_timeout) 
+                response_json = response.json()
+                if response.status_code != 200:
+                    raise OpenAIError(status_code=response.status_code, message=response.text, request=response.request, response=response)
+                
+                ## RESPONSE OBJECT
+                return convert_to_model_response_object(response_object=response_json, model_response_object=model_response)
         except Exception as e: 
             if isinstance(e, httpx.TimeoutException):
                 raise OpenAIError(status_code=500, message="Request Timeout Error")
@@ -292,9 +290,7 @@ class OpenAIChatCompletion(BaseLLM):
                   model_response: ModelResponse, 
                   model: str
     ):
-        if self._client_session is None:
-            self._client_session = self.create_client_session()
-        with self._client_session.stream(
+        with httpx.stream(
                     url=f"{api_base}", # type: ignore
                     json=data,
                     headers=headers,
@@ -316,9 +312,8 @@ class OpenAIChatCompletion(BaseLLM):
                           headers: dict, 
                           model_response: ModelResponse, 
                           model: str):
-        if self._aclient_session is None:
-            self._aclient_session = self.create_aclient_session()
-        async with self._aclient_session.stream(
+        client = httpx.AsyncClient()
+        async with client.stream(
                     url=f"{api_base}",
                     json=data,
                     headers=headers,
@@ -361,7 +356,7 @@ class OpenAIChatCompletion(BaseLLM):
                     additional_args={"complete_input_dict": data},
                 )
             ## COMPLETION CALL
-            response = self._client_session.post(
+            response = httpx.post(
                 api_base, headers=headers, json=data, timeout=litellm.request_timeout
             )
             ## LOGGING

litellm/tests/test_completion.py

@@ -9,9 +9,8 @@ sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
 import pytest
-from openai import Timeout
 import litellm
-from litellm import embedding, completion, completion_cost
+from litellm import embedding, completion, completion_cost, Timeout
 from litellm import RateLimitError
 litellm.num_retries = 3
 litellm.cache = None
@@ -419,7 +418,7 @@ def test_completion_openai():
         pass
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
-test_completion_openai()
+# test_completion_openai()
 
 def test_completion_text_openai():
     try:
@@ -442,11 +441,13 @@ def test_completion_openai_with_optional_params():
         )
         # Add any assertions here to check the response
         print(response)
-    except Timeout as e: 
+    except litellm.Timeout as e: 
         pass
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
 
+test_completion_openai_with_optional_params()
+
 def test_completion_openai_litellm_key():
     try:
         litellm.api_key = os.environ['OPENAI_API_KEY']
@@ -606,7 +607,7 @@ def test_completion_openai_azure_with_functions():
         print(response)
     except Exception as e:
         pytest.fail(f"Error occurred: {e}")
-test_completion_openai_azure_with_functions()
+# test_completion_openai_azure_with_functions()
 
 
 def test_completion_azure():

litellm/tests/test_llmonitor_integration.py

@@ -1,76 +1,76 @@
-#### What this tests ####
-#    This tests if logging to the llmonitor integration actually works
-# Adds the parent directory to the system path
-import sys
-import os
+# #### What this tests ####
+# #    This tests if logging to the llmonitor integration actually works
+# # Adds the parent directory to the system path
+# import sys
+# import os
 
-sys.path.insert(0, os.path.abspath("../.."))
+# sys.path.insert(0, os.path.abspath("../.."))
 
-from litellm import completion, embedding
-import litellm
+# from litellm import completion, embedding
+# import litellm
 
-litellm.success_callback = ["llmonitor"]
-litellm.failure_callback = ["llmonitor"]
+# litellm.success_callback = ["llmonitor"]
+# litellm.failure_callback = ["llmonitor"]
 
-litellm.set_verbose = True
+# litellm.set_verbose = True
 
 
-def test_chat_openai():
-    try:
-        response = completion(
-            model="gpt-3.5-turbo",
-            messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
-            user="ishaan_from_litellm"
-        )
+# def test_chat_openai():
+#     try:
+#         response = completion(
+#             model="gpt-3.5-turbo",
+#             messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
+#             user="ishaan_from_litellm"
+#         )
 
-        print(response)
+#         print(response)
 
-    except Exception as e:
-        print(e)
+#     except Exception as e:
+#         print(e)
 
 
-def test_embedding_openai():
-    try:
-        response = embedding(model="text-embedding-ada-002", input=["test"])
-        # Add any assertions here to check the response
-        print(f"response: {str(response)[:50]}")
-    except Exception as e:
-        print(e)
+# def test_embedding_openai():
+#     try:
+#         response = embedding(model="text-embedding-ada-002", input=["test"])
+#         # Add any assertions here to check the response
+#         print(f"response: {str(response)[:50]}")
+#     except Exception as e:
+#         print(e)
 
 
-test_chat_openai()
-# test_embedding_openai()
+# test_chat_openai()
+# # test_embedding_openai()
 
 
-def test_llmonitor_logging_function_calling():
-    function1 = [
-        {
-            "name": "get_current_weather",
-            "description": "Get the current weather in a given location",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "location": {
-                        "type": "string",
-                        "description": "The city and state, e.g. San Francisco, CA",
-                    },
-                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
-                },
-                "required": ["location"],
-            },
-        }
-    ]
-    try:
-        response = completion(model="gpt-3.5-turbo",
-                              messages=[{
-                                  "role": "user",
-                                  "content": "what's the weather in boston"
-                              }],
-                              temperature=0.1,
-                              functions=function1,
-            )
-        print(response)
-    except Exception as e:
-        print(e)
+# def test_llmonitor_logging_function_calling():
+#     function1 = [
+#         {
+#             "name": "get_current_weather",
+#             "description": "Get the current weather in a given location",
+#             "parameters": {
+#                 "type": "object",
+#                 "properties": {
+#                     "location": {
+#                         "type": "string",
+#                         "description": "The city and state, e.g. San Francisco, CA",
+#                     },
+#                     "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
+#                 },
+#                 "required": ["location"],
+#             },
+#         }
+#     ]
+#     try:
+#         response = completion(model="gpt-3.5-turbo",
+#                               messages=[{
+#                                   "role": "user",
+#                                   "content": "what's the weather in boston"
+#                               }],
+#                               temperature=0.1,
+#                               functions=function1,
+#             )
+#         print(response)
+#     except Exception as e:
+#         print(e)
 
-# test_llmonitor_logging_function_calling()
+# # test_llmonitor_logging_function_calling()