Traceback (most recent call last): File "<input>", line 12, in <module> File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 402, in invoke self.generate_prompt( ~~~~~~~~~~~~~~~~~~~~^ [self._convert_input(input)], ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ...<6 lines>... **kwargs, ^^^^^^^^^ ).generations[0][0], ^ File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1123, in generate_prompt return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs) ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 933, in generate self._generate_with_cache( ~~~~~~~~~~~~~~~~~~~~~~~~~^ m, ^^ ...<2 lines>... **kwargs, ^^^^^^^^^ ) ^ File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_core\language_models\chat_models.py", line 1235, in _generate_with_cache result = self._generate( messages, stop=stop, run_manager=run_manager, **kwargs ) File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_openai\chat_models\base.py", line 1496, in _generate raise e File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\langchain_openai\chat_models\base.py", line 1474, in _generate raw_response = self.root_client.responses.with_raw_response.create( **payload ) File "C:\Users\ml-na\PycharmProjects\pipeline-llm.venv\Lib\site-packages\openai_legacy_response.py", line 367, in wrapped return cast(LegacyAPIResponse[R], func(*args, **kwargs)) ~~~~^^^^^^^^^^^^^^^^^ TypeError: Responses.create() got an unexpected keyword argument 'logprobs'

Fix Plan

To fix the issue, you need to modify the logprobs parameter when using use_responses_api=True. The logprobs parameter is not supported in the responses.create method. Instead, you should use the include parameter to specify the fields you want to include in the response.

Here are the steps to fix the issue:

• Replace logprobs=True with include=["message.output_text.logprobs"] when creating the ChatOpenAI client.
• Update the code to parse the logprobs from the response correctly.

Code Changes

from langchain_openai import ChatOpenAI

client = ChatOpenAI(
    model="gpt-5.2",
    use_responses_api=True,
    include=["message.output_text.logprobs"]
)

response = client.invoke("say hello world")

To parse the logprobs from the response, you can access the logprobs field in the output_text section of the response:

logprobs = response.response_metadata["logprobs"]

However, since the response format has changed, you may need to update the code to parse the logprobs correctly.

Verification

To verify that the fix worked, you can check the response metadata to see if the logprobs are included:

print(response.response_metadata)

This should output the response metadata, including the logprobs.

Extra Tips

• Make sure to update the code to handle any errors that may occur when parsing the logprobs.
• If you're using an older version of the langchain_openai library, you may need to update to the latest version to use the include parameter.
• You can refer to the OpenAI documentation for more information on the include parameter and the response format.