■ ChatOpenAI 클래스의 with_fallbacks 메소드를 사용해 모델 오류시 다른 모델로 대체하는 RunnableWithFallbacks 객체를 만드는 방법을 보여준다.
※ 본 예제에서는 ChatOpenAI 모델에 강제로 오류를 발생시켜서 테스트한다.
※ 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 41 42 |
import httpx from unittest.mock import patch from dotenv import load_dotenv from openai import RateLimitError from langchain_community.llms import GPT4All from langchain_openai import ChatOpenAI load_dotenv() request = httpx.Request("GET", "/") response = httpx.Response(200, request = request) rateLimitError = RateLimitError("rate limit", response = response, body = "") gpt4All = GPT4All(model = "./llama-2-13b-chat.Q4_0.gguf", backend = "llama") chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo-0125", max_retries = 0) runnableWithFallbacks = chatOpenAI.with_fallbacks([gpt4All]) with patch("openai.resources.chat.completions.Completions.create", side_effect = rateLimitError): try: print(chatOpenAI.invoke("Why did the chicken cross the road?")) except RateLimitError: print("Hit error") with patch("openai.resources.chat.completions.Completions.create", side_effect = rateLimitError): try: print(runnableWithFallbacks.invoke("Why did the chicken cross the road?")) except RateLimitError: print("Hit error") """ Hit error To get to the other side! """ |
※ llama-2-13b-chat.Q4_0.gguf 모델 파일은 https://gpt4all.io 웹 사이트에서 다운로드 받은 [Desktop Chat Client] 프로그램에서 다운로드 받을 수 있다.
▶ 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 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
aiohttp==3.9.5 aiosignal==1.3.1 annotated-types==0.7.0 anyio==4.4.0 async-timeout==4.0.3 attrs==23.2.0 certifi==2024.6.2 charset-normalizer==3.3.2 dataclasses-json==0.6.7 distro==1.9.0 exceptiongroup==1.2.1 frozenlist==1.4.1 gpt4all==2.7.0 greenlet==3.0.3 h11==0.14.0 httpcore==1.0.5 httpx==0.27.0 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain==0.2.5 langchain-community==0.2.5 langchain-core==0.2.9 langchain-openai==0.1.9 langchain-text-splitters==0.2.1 langsmith==0.1.81 marshmallow==3.21.3 multidict==6.0.5 mypy-extensions==1.0.0 numpy==1.26.4 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 SQLAlchemy==2.0.31 tenacity==8.4.1 tiktoken==0.7.0 tqdm==4.66.4 typing-inspect==0.9.0 typing_extensions==4.12.2 urllib3==2.2.2 yarl==1.9.4 |
※ psp install httpx python-dotenv langchain langchain-community langchain-openai openai gpt4all 명령을 실행했다.