Function calling broken with Azure OpenAI

[shouryan01]

Describe the bug

To confirm the model works, I asked it to write a haiku:

Next, to test the project, I asked it for python script for hello world

It asked me if I want to execute the script, to which I replied yes. This is when it failed. Here is the complete output:

Yes

    Python Version: 3.12.2
    Pip Version: 24.0
    Open-interpreter Version: cmd:Interpreter, pkg: 0.2.0
    OS Version and Architecture: Windows-10-10.0.19045-SP0
    CPU Info: Intel64 Family 6 Model 183 Stepping 1, GenuineIntel
    RAM Info: 63.69 GB, used: 24.82, free: 38.87

    # Interpreter Info

    Vision: False
    Model: azure/gpt-35-turbo-16k
    Function calling: True
    Context window: 16000
    Max tokens: None

    Auto run: False
    API base: None
    Offline: False

    Curl output: Not local

    # Messages

    System Message: You are Open Interpreter, a world-class programmer that can complete any goal by executing code.

First, write a plan. Always recap the plan between each code block (you have extreme short-term memory loss, so you need to recap the plan between each message block to retain it). When you execute code, it will be executed on the user's machine. The user has given you full and complete permission to execute any code necessary to complete the task. Execute the code. If you want to send data between programming languages, save the data to a txt or json. You can access the internet. Run any code to achieve the goal, and if at first you don't succeed, try again and again. You can install new packages. When a user refers to a filename, they're likely referring to an existing file in the directory you're currently executing code in. Write messages to the user in Markdown. In general, try to make plans with as few steps as possible. As for actually executing code to carry out that plan, for stateful languages (like python, javascript, shell, but NOT for html which starts from 0 every time) it's critical not to try to do everything in one code block. You should try something, print information about it, then continue from there in tiny, informed steps. You will never get it on the first try, and attempting it in one go will often lead to errors you cant see. You are capable of any task.

    {'role': 'user', 'type': 'message', 'content': 'python script for hello world'}

{'role': 'assistant', 'type': 'message', 'content': 'Sure! Here\'s a Python script that prints "Hello, World!" to the console:\n\npython\nprint("Hello, World!")\n\n\nWould you like me to execute this script for you?'}

{'role': 'user', 'type': 'message', 'content': 'Yes'}

Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "C:\Users[redacted]\Personal Projects\openinterpreter\Scripts\interpreter.exe__main__.py", line 7, in File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\core.py", line 25, in start_terminal_interface start_terminal_interface(self) File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\terminal_interface\start_terminal_interface.py", line 684, in start_terminalinterface interpreter.chat() File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\core.py", line 86, in chat for in self._streaming_chat(message=message, display=display): File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\core.py", line 113, in _streaming_chat yield from terminal_interface(self, message) File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\terminal_interface\terminal_interface.py", line 135, in terminal_interface for chunk in interpreter.chat(message, display=False, stream=True): File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\core.py", line 148, in _streaming_chat yield from self._respond_and_store() File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\core.py", line 194, in _respond_and_store for chunk in respond(self): File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\respond.py", line 49, in respond for chunk in interpreter.llm.run(messages_for_llm): File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\llm\llm.py", line 191, in run yield from run_function_calling_llm(self, params) File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\llm\run_function_calling_llm.py", line 66, in run_function_calling_llm arguments = parse_partial_json(arguments) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users[redacted]\Personal Projects\openinterpreter\Lib\site-packages\interpreter\core\llm\utils\parse_partial_json.py", line 8, in parse_partial_json return json.loads(s) ^^^^^^^^^^^^^ File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.752.0_x64qbz5n2kfra8p0\Lib\json\init__.py", line 339, in loads raise TypeError(f'the JSON object must be str, bytes or bytearray, ' TypeError: the JSON object must be str, bytes or bytearray, not NoneType

Reproduce

Command run: interpreter --model azure/gpt-35-turbo-16k --temperature 0.11 --context_window 16000 --llm_supports_functions Model version: 0613 (which according to OpenAI supports function calling.

Expected behavior

It would run the print() statement and output "Hello, World!"

Screenshots

No response

Open Interpreter version

0.2.0

Python version

Tested on: Python 3.11.8 and Python 3.12.2

Operating System name and version

Windows 10 Enterprise

Additional context

No response

[Notnaton]

I think a fix for this has been merged, should be available next update. If you want to test it out, you can install the latest directly from the github repo (keep in mind it can break):

pip install git
pip install git+https://github.com/KillianLucas/open-interpreter.git

[MikeBirdTech]

Hi @shouryan01 Can you please try with the latest version of OI?