OpenAI APIの新機能 Function Callingの詳細解説記事 "How to call functions with chat models" のメモ

背景

OpenAI のAPIドキュメント にもFunction Callingの簡単な説明がありましたが、簡易的すぎるので、もう少し詳細に説明した How_to_call_functions_with_chat_models を読んでいきます。

Function Callingとは

The purpose of this is to enable models to generate function arguments which adhere to the provided specifications.

関数の呼び出しの引数の生成を目的とした機能です

Basic Concept

まずsystem ロールに以下のプロンプトを定義しています。 これによって、GPT側で勝手に引数を推測することを禁止し、ユーザーに定義してもらうようにしています。

{"role": "system", "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."}

functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "format": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"],
                    "description": "The temperature unit to use. Infer this from the users location.",
                },
            },
            "required": ["location", "format"],
        },
    },
    {
        "name": "get_n_day_weather_forecast",
        "description": "Get an N-day weather forecast",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "format": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"],
                    "description": "The temperature unit to use. Infer this from the users location.",
                },
                "num_days": {
                    "type": "integer",
                    "description": "The number of days to forecast",
                }
            },
            "required": ["location", "format", "num_days"]
        },
    },
]

このような関数を定義してchat_completionを呼び出します。

例えば

messages = []
messages.append({"role": "system", "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous."})
messages.append({"role": "user", "content": "What's the weather like today"})
chat_response = chat_completion_request(
    messages, functions=functions
)
assistant_message = chat_response.json()["choices"][0]["message"]
messages.append(assistant_message)
assistant_message

と呼び出すと、 In which city and state would you like to know the current weather?　と返ってきます。つまり、関数呼び出しに必要な情報が集まるまで、chatGPTは情報を集めようと会話を続けようとしてくれます。