转换链（Transformation Chain）

本文档展示了如何使用通用的转换链。

我们将创建一个虚拟的转换链示例。它接受一个非常长的文本，将文本过滤为只包含前三个段落的内容，然后将其传递给一个LLMChain来对其进行摘要。

from langchain.chains import TransformChain, LLMChain, SimpleSequentialChain
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate

with open("../../state_of_the_union.txt") as f:
    state_of_the_union = f.read()

def transform_func(inputs: dict) -> dict:
    text = inputs["text"]
    shortened_text = "\n\n".join(text.split("\n\n")[:3])
    return {"output_text": shortened_text}

transform_chain = TransformChain(input_variables=["text"], output_variables=["output_text"], transform=transform_func)

template = """Summarize this text:

{output_text}

Summary:"""
prompt = PromptTemplate(input_variables=["output_text"], template=template)
llm_chain = LLMChain(llm=OpenAI(), prompt=prompt)

sequential_chain = SimpleSequentialChain(chains=[transform_chain, llm_chain])

sequential_chain.run(state_of_the_union)

' The speaker addresses the nation, noting that while last year they were kept apart due to COVID-19, this year they are together again. They are reminded that regardless of their political affiliations, they are all Americans.'