TypeError: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given

[mwarqee]

Currently testing the Society of Mind notebook and encountering the issue mentioned in the title.
One important difference with respect to the original notebook - instead of loading the credentials via json file, this is done via env file.

config_file_or_env = ".env"
llm_config = {"temperature": 0,"timeout": 600,"cache_seed": 44}
config_list = autogen.config_list_from_dotenv(config_file_or_env, model_api_key_map={'gpt-4o-mini':'OPENAI_API_KEY'},filter_dict={"model": ["gpt-4o-mini"]})

env file content

OPENAI_API_KEY="ewohizhf98328uiefujkc3"
endpoint="https://loremipsum.openai.azure.com"
model="gpt-4o-mini"
api_type="azure"
api_version="2024-08-01-preview"

Getting the following error message -

[autogen.oai.client: 01-10 09:22:29] {250} WARNING - The API key specified is not a valid OpenAI format; it won't work with the OpenAI-hosted model.
WARNING:autogen.oai.client:The API key specified is not a valid OpenAI format; it won't work with the OpenAI-hosted model.
user_proxy (to society_of_mind):

On which days in 2024 was Microsoft Stock higher than $370?

--------------------------------------------------------------------------------

>>>>>>>> USING AUTO REPLY...
society_of_mind (to chat_manager):

On which days in 2024 was Microsoft Stock higher than $370?

--------------------------------------------------------------------------------

Next speaker: inner-assistant

Traceback (most recent call last):
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\contrib\society_of_mind_agent.py", line 198, in generate_inner_monologue_reply
    self.initiate_chat(self.chat_manager, message=messages[-1], clear_history=False)
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 1117, in initiate_chat
    self.send(msg2send, recipient, silent=silent)
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 807, in send
    recipient.receive(message, self, request_reply, silent)
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 917, in receive
    reply = self.generate_reply(messages=self.chat_messages[sender], sender=sender)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 2065, in generate_reply
    final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\groupchat.py", line 1184, in run_chat
    reply = speaker.generate_reply(sender=self)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 2065, in generate_reply
    final, reply = reply_func(self, messages=messages, sender=sender, config=reply_func_tuple["config"])
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 1436, in generate_oai_reply
    extracted_response = self._generate_oai_reply_from_client(
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\autogen\agentchat\conversable_agent.py", line 1455, in _generate_oai_reply_from_client
    response = llm_client.create(
               ^^^^^^^^^^^^^^^^^^
...
               ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "c:\Projects\AutoGenStudio\.vcagent\Lib\site-packages\openai\_utils\_utils.py", line 278, in wrapper
    raise TypeError(msg)
TypeError: Missing required arguments; Expected either ('messages' and 'model') or ('messages', 'model' and 'stream') arguments to be given
Output is truncated. View as a [scrollable element](command:cellOutput.enableScrolling?7d887e2f-44d9-45e0-ba40-6bd61a9cbb3b) or open in a [text editor](command:workbench.action.openLargeOutput?7d887e2f-44d9-45e0-ba40-6bd61a9cbb3b). Adjust cell output [settings](command:workbench.action.openSettings?%5B%22%40tag%3AnotebookOutputLayout%22%5D)...

Is there a sample file showing how to properly load endpoint, api version, api key and model from env for azure?

[jackgerrits]

What version of autogen are you using?