提升Graph-RAG查询生成的秘密武器：最佳提示策略

本文链接：https://blog.csdn.net/tt_jishu/article/details/142321566

引言

在现代数据驱动的世界中，图数据库正在变得越来越重要，尤其是在复杂的关系数据需要高效处理的场景中。本文旨在探讨如何优化图数据库查询生成，特别是在使用大语言模型（LLM）时的提示策略。我们将专注于如何在提示中获取与数据库相关的特定信息。

主要内容

环境设置

首先，我们需要安装必要的包并设置环境变量：

%pip install --upgrade --quiet langchain langchain-community langchain-openai neo4j

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()  # 输入你的OpenAI API密钥

# 指定Neo4j数据库的凭据
os.environ["NEO4J_URI"] = "bolt://localhost:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "password"

连接和数据导入

我们将使用Neo4jGraph连接Neo4j数据库，并导入关于电影和演员的示例数据。

from langchain_community.graphs import Neo4jGraph

graph = Neo4jGraph()

movies_query = """
LOAD CSV WITH HEADERS FROM 
'https://raw.githubusercontent.com/tomasonjo/blog-datasets/main/movies/movies_small.csv'
AS row
MERGE (m:Movie {id:row.movieId})
SET m.released = date(row.released),
    m.title = row.title,
    m.imdbRating = toFloat(row.imdbRating)
FOREACH (director in split(row.director, '|') | 
    MERGE (p:Person {name:trim(director)})
    MERGE (p)-[:DIRECTED]->(m))
FOREACH (actor in split(row.actors, '|') | 
    MERGE (p:Person {name:trim(actor)})
    MERGE (p)-[:ACTED_IN]->(m))
FOREACH (genre in split(row.genres, '|') | 
    MERGE (g:Genre {name:trim(genre)})
    MERGE (m)-[:IN_GENRE]->(g))
"""

graph.query(movies_query)

提示优化策略

过滤图模式

有时，我们可能需要在生成Cypher语句时专注于图模式的特定子集。例如，排除Genre节点：

from langchain.chains import GraphCypherQAChain
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
chain = GraphCypherQAChain.from_llm(
    graph=graph, llm=llm, exclude_types=["Genre"], verbose=True
)

Few-shot 示例

提供自然语言问题转换为Cypher查询的示例可以提高模型的表现，尤其是复杂查询：

from langchain_core.prompts import FewShotPromptTemplate, PromptTemplate

examples = [
    {
        "question": "How many artists are there?",
        "query": "MATCH (a:Person)-[:ACTED_IN]->(:Movie) RETURN count(DISTINCT a)",
    },
    # 更多示例...
]

prompt = FewShotPromptTemplate(
    examples=examples[:5],
    example_prompt=PromptTemplate.from_template(
        "User input: {question}\nCypher query: {query}"
    ),
    prefix="You are a Neo4j expert...",
    suffix="User input: {question}\nCypher query: ",
    input_variables=["question", "schema"],
)

动态 Few-shot 示例

使用 SemanticSimilarityExampleSelector 根据输入动态选择最相关的示例：

from langchain_community.vectorstores import Neo4jVector
from langchain_core.example_selectors import SemanticSimilarityExampleSelector
from langchain_openai import OpenAIEmbeddings

example_selector = SemanticSimilarityExampleSelector.from_examples(
    examples,
    OpenAIEmbeddings(),
    Neo4jVector,
    k=5,
    input_keys=["question"],
)

代码示例

以下是如何使用这些提示策略生成和执行Cypher查询的完整示例：

llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
chain = GraphCypherQAChain.from_llm(
    graph=graph, llm=llm, cypher_prompt=prompt, verbose=True
)

result = chain.invoke("How many actors are in the graph?")
print(result)  # 输出查询结果