mem0 feat(LM Studio): Add response_format param for LM Studio to config

Description

Thank you for checking this PR! Added a “param” parameter to configure the response_format for LM Studio as desired.

Background: LM Studio: 0.3.14 mem0: 0.1.81

I got the following error when using Mem0 with LMStudio. To avoid this error, we would like to be able to specify an arbitrary response_format in config's param.

Traceback (most recent call last):
  File "/Users/*************/workspace/py_prj/agent_practice/mem.py", line 77, in <module>
    m.add(messages, user_id="alice123", metadata={"category": "movies"})
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/mem0/memory/main.py", line 158, in add
    vector_store_result = future1.result()
                          ^^^^^^^^^^^^^^^^
  File "/Users/*************/.local/share/uv/python/cpython-3.12.7-macos-aarch64-none/lib/python3.12/concurrent/futures/_base.py", line 449, in result
    return self.__get_result()
           ^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/.local/share/uv/python/cpython-3.12.7-macos-aarch64-none/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
    raise self._exception
  File "/Users/*************/.local/share/uv/python/cpython-3.12.7-macos-aarch64-none/lib/python3.12/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/mem0/memory/main.py", line 197, in _add_to_vector_store
    response = self.llm.generate_response(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/mem0/llms/lmstudio.py", line 50, in generate_response
    response = self.client.chat.completions.create(**params)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/openai/_utils/_utils.py", line 279, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/openai/resources/chat/completions/completions.py", line 914, in create
    return self._post(
           ^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1242, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 919, in request
    return self._request(
           ^^^^^^^^^^^^^^
  File "/Users/*************/workspace/py_prj/agent_practice/.venv/lib/python3.12/site-packages/openai/_base_client.py", line 1023, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - {'error': "'response_format.type' must be 'json_schema'"}

We would like to be able to specify in the following way

config = {
    "llm": {
        "provider": "lmstudio",
        "config": {
            "model": "meta-llama-3.1-70b-instruct",
            "temperature": 0.2,
            "max_tokens": 2000,
            "lmstudio_base_url": "http://127.0.0.1:1234/v1", # default LM Studio API URL
            "lmstudio_response_format": {"type": "json_schema", "json_schema": {"type": "object", "schema": {}}},
        }
    },
}

Thank you so much for considering this PR.

P.S. We did not know where to find the documentation for the change. Could you tell me where and how to change it.

Fixes # (issue)

Type of change

Please delete options that are not relevant.

[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] Refactor (does not change functionality, e.g. code style improvements, linting)
[ ] Documentation update

How Has This Been Tested?

Added test_generate_response_specifying_response_format. This is a test case to verify that the specified response_format is reflected. Conventional tests have also been performed to confirm that when response_format is not set in config, the same params as before are used.