使用语义层提升图数据库的智能查询能力：从Cypher模板开始

最新推荐文章于 2024-09-24 10:50:41 发布

tt_jishu

最新推荐文章于 2024-09-24 10:50:41 发布

阅读量345

点赞数 3

文章标签：数据库 oracle python

本文链接：https://blog.csdn.net/tt_jishu/article/details/142321305

版权

引言

在现代数据管理中，图数据库如Neo4j被广泛用于存储复杂的关系数据。然而，传统的查询方式可能对初学者和非技术人员较为困难。通过引入语义层，我们能简化这一过程，让智能代理（如LLM）更有效地与数据库交互。本文将探讨如何使用Cypher模板构建语义层，以便在不直接生成复杂查询的情况下从图数据库中检索信息。

主要内容

设置环境

首先，我们需要安装必要的Python包和设置环境变量：

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

import getpass
import os

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

# Neo4j 数据库配置
os.environ["NEO4J_URI"] = "bolt://localhost:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "password"

初始化数据库

建立与Neo4j的连接，并导入示例数据：

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)

使用Cypher模板构建自定义工具

定义Cypher模板，用于从数据库中获取电影或演员信息：

description_query = """
MATCH (m:Movie|Person)
WHERE m.title CONTAINS $candidate OR m.name CONTAINS $candidate
MATCH (m)-[r:ACTED_IN|HAS_GENRE]-(t)
WITH m, type(r) as type, collect(coalesce(t.name, t.title)) as names
WITH m, type+": "+reduce(s="", n IN names | s + n + ", ") as types
WITH m, collect(types) as contexts
WITH m, "type:" + labels(m)[0] + "\ntitle: "+ coalesce(m.title, m.name) 
       + "\nyear: "+coalesce(m.released,"") +"\n" +
       reduce(s="", c in contexts | s + substring(c, 0, size(c)-2) +"\n") as context
RETURN context LIMIT 1
"""

def get_information(entity: str) -> str:
    try:
        data = graph.query(description_query, params={"candidate": entity})
        return data[0]["context"]
    except IndexError:
        return "No information was found"

创建语义工具

使用LLM代理来调用我们定义的工具：

from langchain.pydantic_v1 import BaseModel, Field
from langchain_core.callbacks import CallbackManagerForToolRun
from langchain_core.tools import BaseTool

class InformationInput(BaseModel):
    entity: str = Field(description="电影或演员名称")

class InformationTool(BaseTool):
    name = "Information"
    description = "提供有关电影或演员的信息查询"
    args_schema: Type[BaseModel] = InformationInput

    def _run(self, entity: str, run_manager: Optional[CallbackManagerForToolRun] = None) -> str:
        return get_information(entity)

创建并执行代理

定义与数据库的交互逻辑：

from typing import List, Tuple
from langchain.agents import AgentExecutor
from langchain_core.messages import AIMessage, HumanMessage
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
tools = [InformationTool()]

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "您是一个帮助查找电影信息的智能助手。请根据需要询问问题，以帮助用户获得更精确的信息。"),
        MessagesPlaceholder(variable_name="chat_history"),
        ("user", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad"),
    ]
)

agent_executor = AgentExecutor(agent=prompt.bind(llm.bind(tools)), tools=tools, verbose=True)

agent_executor.invoke({"input": "Who played in Casino?"})