Support multiple function calling

[rgbkrk]

As requested in MeetKai/functionary#59 (comment)

we are training a new functionary model with the ability to call multiple functions in parallel; it is similar to OpenAI parallel function call. Hope that Chatlab will support this soon ?

[rgbkrk]

Example from Parallel Function Calling

    response = client.chat.completions.create(
        model="gpt-3.5-turbo-1106",
        messages=messages,
        tools=tools,
        tool_choice="auto",  # auto is default, but we'll be explicit
    )
    response_message = response.choices[0].message
    tool_calls = response_message.tool_calls
    # Step 2: check if the model wanted to call a function
    if tool_calls:
        # Step 3: call the function
        # Note: the JSON response may not always be valid; be sure to handle errors
        available_functions = {
            "get_current_weather": get_current_weather,
        }  # only one function in this example, but you can have multiple
        messages.append(response_message)  # extend conversation with assistant's reply
        # Step 4: send the info for each function call and function response to the model
        for tool_call in tool_calls:
            function_name = tool_call.function.name
            function_to_call = available_functions[function_name]
            function_args = json.loads(tool_call.function.arguments)
            function_response = function_to_call(
                location=function_args.get("location"),
                unit=function_args.get("unit"),
            )
            messages.append(
                {
                    "tool_call_id": tool_call.id,
                    "role": "tool",
                    "name": function_name,
                    "content": function_response,
                }
            )  # extend conversation with function response
        second_response = client.chat.completions.create(
            model="gpt-3.5-turbo-1106",
            messages=messages,
        )  # get a new response from the model where it can see the function response
        return second_response

[musab-mk]

Hi, Do you have any updates on this? We would love to add chatlab's parallel calls into the functionary. Thanks!

[rgbkrk]

On it today, thanks for the bump @musab-mk. #122

[rgbkrk]

1.3.0 has this in. I'll work on a PR for functionary next. Note that I will use the llama.cpp setup instead due to being on a Mac for local testing.

[musabgultekin]

Thank you @rgbkrk !

[rgbkrk]

Looking great with functionary!

[rgbkrk]

PR made in MeetKai/functionary#93

I'll look into how to support this well for the in-notebook Chat as well.