[PYTHON/LANGCHAIN] AIMessage 클래스 : response_metadata 속성 사용하기 (ChatOpenAI 객체 사용시)

■ AIMessage 클래스의 response_metadata 속성을 사용하는 방법을 보여준다. (ChatOpenAI 객체 사용시)

▶ 예제 코드 (PY)


from langchain_openai import ChatOpenAI

chatOpenAI = ChatOpenAI(model = "gpt-4-turbo")

aiMessage = chatOpenAI.invoke([("human", "What's the oldest known example of cuneiform")])

print(aiMessage.response_metadata)

"""
{
    'token_usage' : {
        'completion_tokens' : 164,
        'prompt_tokens'     : 17,
        'total_tokens'      : 181
    },
    'model_name'         : 'gpt-4-turbo',
    'system_fingerprint' : 'fp_76f018034d',
    'finish_reason'      : 'stop',
    'logprobs'           : None
}
"""

from langchain_openai import ChatOpenAI

chatOpenAI = ChatOpenAI(model = "gpt-4-turbo")

aiMessage = chatOpenAI.invoke([("human", "What's the oldest known example of cuneiform")])

print(aiMessage.response_metadata)

"""

{

'token_usage' : {

'completion_tokens' : 164,

'prompt_tokens' : 17,

'total_tokens' : 181

'model_name' : 'gpt-4-turbo',

'system_fingerprint' : 'fp_76f018034d',

'finish_reason' : 'stop',

'logprobs' : None

}

"""