■ ChatOpenAI 클래스의 생성자에서 model_kwargs 인자를 설정해서 토큰 사용량을 구하는 방법을 보여준다.
※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다.
▶ main.py
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
import asyncio from dotenv import load_dotenv from langchain_core.pydantic_v1 import BaseModel, Field from langchain_openai import ChatOpenAI async def main(): load_dotenv() class Joke(BaseModel): """Joke to tell user.""" setup : str = Field(description = "question to set up a joke" ) punchline : str = Field(description = "answer to resolve the joke") chatOpenAI = ChatOpenAI( model = "gpt-3.5-turbo-0125", model_kwargs = {"stream_options" : {"include_usage" : True}} ) # 내부적으로 .with_structured_output은 도구를 채팅 모델에 바인딩하고 파서를 추가한다. structured_llm = chatOpenAI.with_structured_output(Joke) async for eventDictionary in structured_llm.astream_events("Tell me a joke", version = "v2"): if eventDictionary["event"] == "on_chat_model_end": print(f"Token usage : {eventDictionary["data"]["output"].usage_metadata}\n") elif eventDictionary["event"] == "on_chain_end": print(eventDictionary["data"]["output"]) else: pass asyncio.run(main()) """ Token usage: {'input_tokens': 72, 'output_tokens': 32, 'total_tokens': 104} setup="Why couldn't the bicycle find its way home?" punchline='Because it lost its bearings!' """ |
▶ requirements.txt
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 |
annotated-types==0.7.0 anyio==4.4.0 certifi==2024.6.2 charset-normalizer==3.3.2 distro==1.9.0 exceptiongroup==1.2.1 h11==0.14.0 httpcore==1.0.5 httpx==0.27.0 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain-core==0.2.9 langchain-openai==0.1.9 langsmith==0.1.82 openai==1.35.3 orjson==3.10.5 packaging==24.1 pydantic==2.7.4 pydantic_core==2.18.4 python-dotenv==1.0.1 PyYAML==6.0.1 regex==2024.5.15 requests==2.32.3 sniffio==1.3.1 tenacity==8.4.2 tiktoken==0.7.0 tqdm==4.66.4 typing_extensions==4.12.2 urllib3==2.2.2 |
※ pip install python-dotenv langchain-openai 명령을 실행했다.