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

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

▶ 예제 코드 (PY)


from langchain_groq import ChatGroq

chatGroq = ChatGroq()

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

print(aiMessage.response_metadata)

"""
{
    'token_usage' : {
        'completion_time'   : 0.243,
        'completion_tokens' : 132,
        'prompt_time'       : 0.022,
        'prompt_tokens'     : 22,
        'queue_time'        : None,
        'total_time'        : 0.265,
        'total_tokens'      : 154
    },
    'model_name'         : 'mixtral-8x7b-32768',
    'system_fingerprint' : 'fp_7b44c65f25',
    'finish_reason'      : 'stop',
    'logprobs'           : None
}
"""

from langchain_groq import ChatGroq

chatGroq = ChatGroq()

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

print(aiMessage.response_metadata)

"""

{

'token_usage' : {

'completion_time' : 0.243,

'completion_tokens' : 132,

'prompt_time' : 0.022,

'prompt_tokens' : 22,

'queue_time' : None,

'total_time' : 0.265,

'total_tokens' : 154

'model_name' : 'mixtral-8x7b-32768',

'system_fingerprint' : 'fp_7b44c65f25',

'finish_reason' : 'stop',

'logprobs' : None

}

"""