'Unrecognized request argument supplied: functions' when using azure-openai

[zhh210]

Describe the bug

I'm able to set up AZURE_API_BASE, AZURE_API_KEY, AZURE_API_VERSION but using interpreter still has trouble using azure openai:

Traceback (most recent call last):
  File "/Users/zhh210/installs/anaconda3/bin/interpreter", line 8, in <module>
    sys.exit(interpreter.start_terminal_interface())
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/core.py", line 25, in start_terminal_interface
    start_terminal_interface(self)
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/terminal_interface/start_terminal_interface.py", line 684, in start_terminal_interface
    interpreter.chat()
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/core.py", line 86, in chat
    for _ in self._streaming_chat(message=message, display=display):
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/core.py", line 113, in _streaming_chat
    yield from terminal_interface(self, message)
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/terminal_interface/terminal_interface.py", line 135, in terminal_interface
    for chunk in interpreter.chat(message, display=False, stream=True):
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/core.py", line 148, in _streaming_chat
    yield from self._respond_and_store()
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/core.py", line 194, in _respond_and_store
    for chunk in respond(self):
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/respond.py", line 49, in respond
    for chunk in interpreter.llm.run(messages_for_llm):
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/llm/llm.py", line 191, in run
    yield from run_function_calling_llm(self, params)
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/llm/run_function_calling_llm.py", line 44, in run_function_calling_llm
    for chunk in llm.completions(**request_params):
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/llm/llm.py", line 224, in fixed_litellm_completions
    raise first_error
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/llm/llm.py", line 205, in fixed_litellm_completions
    yield from litellm.completion(**params)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/litellm/utils.py", line 2171, in wrapper
    raise e
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/litellm/utils.py", line 2078, in wrapper
    result = original_function(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/litellm/main.py", line 1808, in completion
    raise exception_type(
          ^^^^^^^^^^^^^^^
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/litellm/utils.py", line 6713, in exception_type
    raise e
  File "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/litellm/utils.py", line 6610, in exception_type
    raise BadRequestError(
litellm.exceptions.BadRequestError: AzureException - Error code: 404 - {'error': {'message': 'Unrecognized request argument supplied: functions', 'type': 'invalid_request_error', 'param': None, 'code': None}}

Reproduce

1. Set up env variables
2. Run interpreter --model azure/gpt-35-turbo

Expected behavior

output expected code and ask if execute

Screenshots

No response

Open Interpreter version

0.2.0

Python version

3.11

Operating System name and version

macOS Darwin

Additional context

No response

[MonsterCoder]

I have the same problem.It is likely the version of your deployment doesn't support function-calling. I have made a pull request to enable passing an argument --no-llm_supports_functions whick will make OP to treat function_calls correctlly. Before this problem is fixed, you can manually set it to fmake it work for you for now. Open "/Users/zhh210/installs/anaconda3/lib/python3.11/site-packages/interpreter/core/llm/llm.py" Find line 30, change from self.supports_functions = None to self.supports_functions = False

[yekamu]

try "llm.supports_functions: False" in your config.yaml