如何为可运行程序添加备用项

在使用语言模型时，你可能会经常遇到底层 API 的问题，无论是速率限制还是停机。因此，当你准备将 LLM 应用投入生产时，防范这些问题变得越来越重要。这就是我们引入“备用项”概念的原因。

备用项是在紧急情况下可以使用的替代计划。

至关重要的是，备用项不仅可以应用于 LLM 层面，还可以应用于整个可运行程序层面。这一点很重要，因为不同的模型通常需要不同的提示。因此，如果你的 OpenAI 调用失败了，你不想仅仅将相同的提示发送给 Anthropic——你可能需要使用不同的提示模板，并将不同的版本发送过去。

LLM API 错误回退

这可能是回退最常见的用例。调用 LLM API 请求可能会因为各种原因失败——API 可能宕机，你可能达到了速率限制，等等。因此，使用回退可以帮助防范这类情况。

重要提示：默认情况下，许多 LLM 包装器会捕获错误并重试。在处理回退时，你可能需要关闭这些功能。否则，第一个包装器会一直重试而不会失败。

%pip install --upgrade --quiet  langchain langchain-openai

from langchain_anthropic import ChatAnthropic
from langchain_openai import ChatOpenAI

API Reference:ChatAnthropic | ChatOpenAI

首先，让我们模拟一下した場合会发生的情况，当我们从 OpenAI 收到 RateLimitError 错误时

from unittest.mock import patch

import httpx
from openai import RateLimitError

request = httpx.Request("GET", "/")
response = httpx.Response(200, request=request)
error = RateLimitError("rate limit", response=response, body="")

# Note that we set max_retries = 0 to avoid retrying on RateLimits, etc
openai_llm = ChatOpenAI(model="gpt-4o-mini", max_retries=0)
anthropic_llm = ChatAnthropic(model="claude-3-haiku-20240307")
llm = openai_llm.with_fallbacks([anthropic_llm])

# Let's use just the OpenAI LLm first, to show that we run into an error
with patch("openai.resources.chat.completions.Completions.create", side_effect=error):
    try:
        print(openai_llm.invoke("Why did the chicken cross the road?"))
    except RateLimitError:
        print("Hit error")

Hit error

# Now let's try with fallbacks to Anthropic
with patch("openai.resources.chat.completions.Completions.create", side_effect=error):
    try:
        print(llm.invoke("Why did the chicken cross the road?"))
    except RateLimitError:
        print("Hit error")

content=' I don\'t actually know why the chicken crossed the road, but here are some possible humorous answers:\n\n- To get to the other side!\n\n- It was too chicken to just stand there. \n\n- It wanted a change of scenery.\n\n- It wanted to show the possum it could be done.\n\n- It was on its way to a poultry farmers\' convention.\n\nThe joke plays on the double meaning of "the other side" - literally crossing the road to the other side, or the "other side" meaning the afterlife. So it\'s an anti-joke, with a silly or unexpected pun as the answer.' additional_kwargs={} example=False

我们可以像使用普通的大语言模型（LLM）一样使用我们的“带后备机制的大语言模型”。

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You're a nice assistant who always includes a compliment in your response",
        ),
        ("human", "Why did the {animal} cross the road"),
    ]
)
chain = prompt | llm
with patch("openai.resources.chat.completions.Completions.create", side_effect=error):
    try:
        print(chain.invoke({"animal": "kangaroo"}))
    except RateLimitError:
        print("Hit error")

API Reference:ChatPromptTemplate

content=" I don't actually know why the kangaroo crossed the road, but I can take a guess! Here are some possible reasons:\n\n- To get to the other side (the classic joke answer!)\n\n- It was trying to find some food or water \n\n- It was trying to find a mate during mating season\n\n- It was fleeing from a predator or perceived threat\n\n- It was disoriented and crossed accidentally \n\n- It was following a herd of other kangaroos who were crossing\n\n- It wanted a change of scenery or environment \n\n- It was trying to reach a new habitat or territory\n\nThe real reason is unknown without more context, but hopefully one of those potential explanations does the joke justice! Let me know if you have any other animal jokes I can try to decipher." additional_kwargs={} example=False

序列的回退

我们也可以为序列创建回退，而这些回退本身也是序列。在这里，我们使用两个不同的模型来实现这一点：ChatOpenAI 和普通的 OpenAI（不使用聊天模型）。因为 OpenAI 不是一个聊天模型，所以你可能需要一个不同的提示。

# First let's create a chain with a ChatModel
# We add in a string output parser here so the outputs between the two are the same type
from langchain_core.output_parsers import StrOutputParser

chat_prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You're a nice assistant who always includes a compliment in your response",
        ),
        ("human", "Why did the {animal} cross the road"),
    ]
)
# Here we're going to use a bad model name to easily create a chain that will error
chat_model = ChatOpenAI(model="gpt-fake")
bad_chain = chat_prompt | chat_model | StrOutputParser()

API Reference:StrOutputParser

# Now lets create a chain with the normal OpenAI model
from langchain_core.prompts import PromptTemplate
from langchain_openai import OpenAI

prompt_template = """Instructions: You should always include a compliment in your response.

Question: Why did the {animal} cross the road?"""
prompt = PromptTemplate.from_template(prompt_template)
llm = OpenAI()
good_chain = prompt | llm

API Reference:PromptTemplate | OpenAI

# We can now create a final chain which combines the two
chain = bad_chain.with_fallbacks([good_chain])
chain.invoke({"animal": "turtle"})

'\n\nAnswer: The turtle crossed the road to get to the other side, and I have to say he had some impressive determination.'

长输入的备用方案

LLM 的一大限制因素是它们的上下文窗口。通常，在将提示发送给 LLM 之前，你可以计算和跟踪其长度，但在难以/复杂的情况下，你可以回退到使用具有更长上下文长度的模型。

short_llm = ChatOpenAI()
long_llm = ChatOpenAI(model="gpt-3.5-turbo-16k")
llm = short_llm.with_fallbacks([long_llm])

inputs = "What is the next number: " + ", ".join(["one", "two"] * 3000)

try:
    print(short_llm.invoke(inputs))
except Exception as e:
    print(e)

This model's maximum context length is 4097 tokens. However, your messages resulted in 12012 tokens. Please reduce the length of the messages.

try:
    print(llm.invoke(inputs))
except Exception as e:
    print(e)

content='The next number in the sequence is two.' additional_kwargs={} example=False

备用更优模型

很多时候，我们会要求模型以特定格式（例如 JSON）输出。像 GPT-3.5 这样的模型可以做得不错，但有时会遇到困难。这自然而然地引出了备用方案——我们可以尝试使用 GPT-3.5（速度更快、成本更低），如果解析失败，我们再使用 GPT-4。

from langchain.output_parsers import DatetimeOutputParser

API Reference:DatetimeOutputParser

prompt = ChatPromptTemplate.from_template(
    "what time was {event} (in %Y-%m-%dT%H:%M:%S.%fZ format - only return this value)"
)

# In this case we are going to do the fallbacks on the LLM + output parser level
# Because the error will get raised in the OutputParser
openai_35 = ChatOpenAI() | DatetimeOutputParser()
openai_4 = ChatOpenAI(model="gpt-4") | DatetimeOutputParser()

only_35 = prompt | openai_35
fallback_4 = prompt | openai_35.with_fallbacks([openai_4])

try:
    print(only_35.invoke({"event": "the superbowl in 1994"}))
except Exception as e:
    print(f"Error: {e}")

Error: Could not parse datetime string: The Super Bowl in 1994 took place on January 30th at 3:30 PM local time. Converting this to the specified format (%Y-%m-%dT%H:%M:%S.%fZ) results in: 1994-01-30T15:30:00.000Z

try:
    print(fallback_4.invoke({"event": "the superbowl in 1994"}))
except Exception as e:
    print(f"Error: {e}")

1994-01-30 15:30:00

LLM API 错误回退​

序列的回退​

长输入的备用方案​

备用更优模型​

LLM API 错误回退

序列的回退

长输入的备用方案

备用更优模型