Functions not called when i use langchain_openai.ChatOpenAI as llm

[Dovahkiin8625]

When I use langchain_openai.ChatOpenAI as llm to make calls to OpenAI tools, the output results do not reflect that any method was called. I noticed that there is no tools parameter in the request body sent to OpenAI, but instead there is a functions parameter. However, the functions parameter has been deprecated.

This is my code:

llm = ChatOpenAI(openai_api_key="xxx",temperature=0.5)
tools = [get_band_packages]
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            system_msg
        ),
        MessagesPlaceholder(variable_name="chat_history"),
        ("user", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)
chat_history = []
functions = [format_tool_to_openai_function(t) for t in tools]
llm_with_tools = llm.bind(functions=functions)
agent = (
        {
            "input": lambda x: x["input"],
            "agent_scratchpad": lambda x: format_to_openai_function_messages(
                x["intermediate_steps"]
            ),
            "chat_history": lambda x: x["chat_history"],
        }
        | prompt
        | llm_with_tools
        | OpenAIFunctionsAgentOutputParser()
)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "xxxxxxx","chat_history":[]})

This is the official documentation of OpenAI.

And here is how langchain-openai bind funcitons:

    def bind_functions(
        self,
        functions: Sequence[Union[Dict[str, Any], Type[BaseModel], Callable]],
        function_call: Optional[str] = None,
        **kwargs: Any,
    ) -> Runnable[LanguageModelInput, BaseMessage]:
        """Bind functions (and other objects) to this chat model.

        Args:
            functions: A list of function definitions to bind to this chat model.
                Can be  a dictionary, pydantic model, or callable. Pydantic
                models and callables will be automatically converted to
                their schema dictionary representation.
            function_call: Which function to require the model to call.
                Must be the name of the single provided function or
                "auto" to automatically determine which function to call
                (if any).
            kwargs: Any additional parameters to pass to the
                :class:`~langchain.runnable.Runnable` constructor.
        """

        formatted_functions = [convert_to_openai_function(fn) for fn in functions]
        if function_call is not None:
            if len(formatted_functions) != 1:
                raise ValueError(
                    "When specifying `function_call`, you must provide exactly one "
                    "function."
                )
            if formatted_functions[0]["name"] != function_call:
                raise ValueError(
                    f"Function call {function_call} was specified, but the only "
                    f"provided function was {formatted_functions[0]['name']}."
                )
            function_call_ = {"name": function_call}
            kwargs = {**kwargs, "function_call": function_call_}
        return super().bind(
            functions=formatted_functions,
            **kwargs,
        )

[dosubot[bot]]

🤖

Hello @Dovahkiin8625!

I'm Dosu, a friendly bot here to assist you in resolving issues, answering queries, and helping you contribute more efficiently to the LangChain project. While we're waiting for a human maintainer to join us, I'm here to make your coding journey smoother. Let's make some software magic together!

Based on the information you've provided, it seems like you're trying to use the functions parameter with the ChatOpenAI class. However, as per the issue #12415 in the LangChain repository, the functions parameter has been deprecated and is no longer recognized by OpenAI.

Instead, you should use the bind_functions method of the ChatOpenAI class to bind your functions to the chat model. This method accepts a list of function definitions, which can be a dictionary, a Pydantic model, or a callable. Pydantic models and callables are automatically converted to their schema dictionary representation.

Here's an example of how you can use the bind_functions method:

llm = ChatOpenAI(openai_api_key="xxx",temperature=0.5)
tools = [get_band_packages]
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            system_msg
        ),
        MessagesPlaceholder(variable_name="chat_history"),
        ("user", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)
chat_history = []
functions = [format_tool_to_openai_function(t) for t in tools]
llm_with_tools = llm.bind_functions(functions=functions)
agent = (
        {
            "input": lambda x: x["input"],
            "agent_scratchpad": lambda x: format_to_openai_function_messages(
                x["intermediate_steps"]
            ),
            "chat_history": lambda x: x["chat_history"],
        }
        | prompt
        | llm_with_tools
        | OpenAIFunctionsAgentOutputParser()
)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "xxxxxxx","chat_history":[]})

In this example, the bind_functions method is used to bind the functions to the llm instance of the ChatOpenAI class. The functions parameter is a list of functions that have been formatted for OpenAI using the format_tool_to_openai_function function.

Please try this approach and let me know if it resolves your issue. If you have any further questions or need additional clarification, feel free to ask.

Sources

• openai.error.InvalidRequestError: Unrecognized request argument supplied: functions
• libs/partners/openai/langchain_openai/chat_models/base.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[dosubot[bot]]

🤖

Hello @Dovahkiin8625!

I'm Dosu, a friendly bot here to assist you in resolving issues, answering queries, and helping you contribute more efficiently to the LangChain project. While we're waiting for a human maintainer to join us, I'm here to make your coding journey smoother. Let's make some software magic together!

Based on the information you've provided, it seems like you're trying to use the functions parameter with the ChatOpenAI class. However, as per the issue #12415 in the LangChain repository, the functions parameter has been deprecated and is no longer recognized by OpenAI.

Instead, you should use the bind_functions method of the ChatOpenAI class to bind your functions to the chat model. This method accepts a list of function definitions, which can be a dictionary, a Pydantic model, or a callable. Pydantic models and callables are automatically converted to their schema dictionary representation.

Here's an example of how you can use the bind_functions method:

llm = ChatOpenAI(openai_api_key="xxx",temperature=0.5)
tools = [get_band_packages]
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            system_msg
        ),
        MessagesPlaceholder(variable_name="chat_history"),
        ("user", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)
chat_history = []
functions = [format_tool_to_openai_function(t) for t in tools]
llm_with_tools = llm.bind_functions(functions=functions)
agent = (
        {
            "input": lambda x: x["input"],
            "agent_scratchpad": lambda x: format_to_openai_function_messages(
                x["intermediate_steps"]
            ),
            "chat_history": lambda x: x["chat_history"],
        }
        | prompt
        | llm_with_tools
        | OpenAIFunctionsAgentOutputParser()
)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "xxxxxxx","chat_history":[]})

In this example, the bind_functions method is used to bind the functions to the llm instance of the ChatOpenAI class. The functions parameter is a list of functions that have been formatted for OpenAI using the format_tool_to_openai_function function.

Please try this approach and let me know if it resolves your issue. If you have any further questions or need additional clarification, feel free to ask.

Sources

• openai.error.InvalidRequestError: Unrecognized request argument supplied: functions
• libs/partners/openai/langchain_openai/chat_models/base.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.