提升Graph-RAG查询生成的有效策略-CSDN博客

本文链接：https://blog.csdn.net/bhawfgrcbtwny/article/details/143224016

提升Graph-RAG查询生成的有效策略

在本指南中，我们将探讨如何通过有效的提示策略来改进图数据库的查询生成，主要集中在如何在提示中获取与数据库相关的信息。

引言

随着图数据库在复杂数据管理中的广泛应用，生成针对性强的查询变得至关重要。Graph-RAG（Graph Reasoning and Generation）的能力依赖于对数据库结构和内容的深刻理解。在这篇文章中，我们将介绍一些实用的提示策略，帮助开发者生成更有效的Cypher查询。

主要内容

环境设置

首先，我们需要安装必要的软件包和设置环境变量：

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

注意：可能需要重启内核以应用更新。

接下来，配置你的API密钥：

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()

如果你使用Neo4j，还需要设置相关凭证：

os.environ["NEO4J_URI"] = "bolt://localhost:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "password"

导入图数据

我们需要创建一个与Neo4j数据库的连接并导入有关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)

筛选图模式

有时，我们需要专注于图模式的特定子集。在这种情况下，可以使用exclude参数来过滤掉不需要的节点或关系类型。

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实例

通过在提示中包含一些自然语言问题及其对应的Cypher查询实例，可以提高模型对复杂查询的生成能力。

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)",
    },
    {
        "question": "Which actors played in the movie Casino?",
        "query": "MATCH (m:Movie {{title: 'Casino'}})<-[:ACTED_IN]-(a) RETURN a.name",
    },
    # 更多实例同样可添加
]

example_prompt = PromptTemplate.from_template(
    "User input: {question}\nCypher query: {query}"
)
prompt = FewShotPromptTemplate(
    examples=examples[:5],
    example_prompt=example_prompt,
    prefix="You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.\n\nHere is the schema information\n{schema}.\n\nBelow are a number of examples of questions and their corresponding Cypher queries.",
    suffix="User input: {question}\nCypher query: ",
    input_variables=["question", "schema"],
)

动态Few-shot实例

通过选择与输入最相关的示例来动态生成few-shot提示，从而提高模型性能。

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"],
)

prompt = FewShotPromptTemplate(
    example_selector=example_selector,
    example_prompt=example_prompt,
    prefix="You are a Neo4j expert. Given an input question, create a syntactically correct Cypher query to run.\n\nHere is the schema information\n{schema}.\n\nBelow are a number of examples of questions and their corresponding Cypher queries.",
    suffix="User input: {question}\nCypher query: ",
    input_variables=["question", "schema"],
)