fix(utils.py): set max_retries = num_retries, if given

litellm/main.py

@@ -762,8 +762,8 @@ def completion(
     try:
         if base_url is not None:
             api_base = base_url
-        if max_retries is not None:  # openai allows openai.OpenAI(max_retries=3)
-            num_retries = max_retries
+        if num_retries is not None:
+            max_retries = num_retries
         logging = litellm_logging_obj
         fallbacks = fallbacks or litellm.model_fallbacks
         if fallbacks is not None:

litellm/tests/test_class.py

@@ -1,5 +1,5 @@
-# #### What this tests ####
-# #    This tests the LiteLLM Class
+# # #### What this tests ####
+# # #    This tests the LiteLLM Class
 
 # import sys, os
 # import traceback
@@ -11,83 +11,114 @@
 # import litellm
 # import asyncio
 
-# litellm.set_verbose = True
-# from litellm import Router
+# # litellm.set_verbose = True
+# # from litellm import Router
 # import instructor
+
+# from litellm import completion
 # from pydantic import BaseModel
 
-# # This enables response_model keyword
-# # from client.chat.completions.create
-# client = instructor.patch(
-#     Router(
-#         model_list=[
-#             {
-#                 "model_name": "gpt-3.5-turbo",  # openai model name
-#                 "litellm_params": {  # params for litellm completion/embedding call
-#                     "model": "azure/chatgpt-v-2",
-#                     "api_key": os.getenv("AZURE_API_KEY"),
-#                     "api_version": os.getenv("AZURE_API_VERSION"),
-#                     "api_base": os.getenv("AZURE_API_BASE"),
-#                 },
-#             }
-#         ]
-#     )
-# )
 
-
-# class UserDetail(BaseModel):
+# class User(BaseModel):
 #     name: str
 #     age: int
 
 
-# user = client.chat.completions.create(
+# client = instructor.from_litellm(completion)
+
+# litellm.set_verbose = True
+
+# resp = client.chat.completions.create(
 #     model="gpt-3.5-turbo",
-#     response_model=UserDetail,
+#     max_tokens=1024,
 #     messages=[
-#         {"role": "user", "content": "Extract Jason is 25 years old"},
+#         {
+#             "role": "user",
+#             "content": "Extract Jason is 25 years old.",
+#         }
 #     ],
+#     response_model=User,
+#     num_retries=10,
 # )
 
-# assert isinstance(user, UserDetail)
-# assert user.name == "Jason"
-# assert user.age == 25
+# assert isinstance(resp, User)
+# assert resp.name == "Jason"
+# assert resp.age == 25
 
-# print(f"user: {user}")
-# # import instructor
-# # from openai import AsyncOpenAI
+# # from pydantic import BaseModel
 
-# aclient = instructor.apatch(
-#     Router(
-#         model_list=[
-#             {
-#                 "model_name": "gpt-3.5-turbo",  # openai model name
-#                 "litellm_params": {  # params for litellm completion/embedding call
-#                     "model": "azure/chatgpt-v-2",
-#                     "api_key": os.getenv("AZURE_API_KEY"),
-#                     "api_version": os.getenv("AZURE_API_VERSION"),
-#                     "api_base": os.getenv("AZURE_API_BASE"),
-#                 },
-#             }
-#         ],
-#         default_litellm_params={"acompletion": True},
-#     )
-# )
+# # # This enables response_model keyword
+# # # from client.chat.completions.create
+# # client = instructor.patch(
+# #     Router(
+# #         model_list=[
+# #             {
+# #                 "model_name": "gpt-3.5-turbo",  # openai model name
+# #                 "litellm_params": {  # params for litellm completion/embedding call
+# #                     "model": "azure/chatgpt-v-2",
+# #                     "api_key": os.getenv("AZURE_API_KEY"),
+# #                     "api_version": os.getenv("AZURE_API_VERSION"),
+# #                     "api_base": os.getenv("AZURE_API_BASE"),
+# #                 },
+# #             }
+# #         ]
+# #     )
+# # )
 
 
-# class UserExtract(BaseModel):
-#     name: str
-#     age: int
+# # class UserDetail(BaseModel):
+# #     name: str
+# #     age: int
 
 
-# async def main():
-#     model = await aclient.chat.completions.create(
-#         model="gpt-3.5-turbo",
-#         response_model=UserExtract,
-#         messages=[
-#             {"role": "user", "content": "Extract jason is 25 years old"},
-#         ],
-#     )
-#     print(f"model: {model}")
+# # user = client.chat.completions.create(
+# #     model="gpt-3.5-turbo",
+# #     response_model=UserDetail,
+# #     messages=[
+# #         {"role": "user", "content": "Extract Jason is 25 years old"},
+# #     ],
+# # )
+
+# # assert isinstance(user, UserDetail)
+# # assert user.name == "Jason"
+# # assert user.age == 25
+
+# # print(f"user: {user}")
+# # # import instructor
+# # # from openai import AsyncOpenAI
+
+# # aclient = instructor.apatch(
+# #     Router(
+# #         model_list=[
+# #             {
+# #                 "model_name": "gpt-3.5-turbo",  # openai model name
+# #                 "litellm_params": {  # params for litellm completion/embedding call
+# #                     "model": "azure/chatgpt-v-2",
+# #                     "api_key": os.getenv("AZURE_API_KEY"),
+# #                     "api_version": os.getenv("AZURE_API_VERSION"),
+# #                     "api_base": os.getenv("AZURE_API_BASE"),
+# #                 },
+# #             }
+# #         ],
+# #         default_litellm_params={"acompletion": True},
+# #     )
+# # )
 
 
-# asyncio.run(main())
+# # class UserExtract(BaseModel):
+# #     name: str
+# #     age: int
+
+
+# # async def main():
+# #     model = await aclient.chat.completions.create(
+# #         model="gpt-3.5-turbo",
+# #         response_model=UserExtract,
+# #         messages=[
+# #             {"role": "user", "content": "Extract jason is 25 years old"},
+# #         ],
+# #     )
+# #     print(f"model: {model}")
+
+
+# # asyncio.run(main())