如何为可运行对象添加回退

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

from langchain_anthropic import ChatAnthropic
from langchain_openai import ChatOpenAI

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")

# 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")

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")

# 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()

# 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

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

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)

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

from langchain.output_parsers import 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}")

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