Skip to main content

图数据库QA链

这个笔记本展示了如何使用LLMs为图数据库提供自然语言接口，您可以使用Cypher查询语言进行查询。

您需要运行一个Neo4j实例。一种选择是在Aura云服务中创建一个免费的Neo4j数据库实例。您还可以使用Neo4j桌面应用程序或运行docker容器在本地运行数据库。 您可以通过执行以下脚本来运行本地docker容器：

docker run \
    --name neo4j \
    -p 7474:7474 -p 7687:7687 \
    -d \
    -e NEO4J_AUTH=neo4j/pleaseletmein \
    -e NEO4J_PLUGINS=\[\"apoc\"\]  \
    neo4j:latest

如果您使用的是docker容器，需要等待几秒钟让数据库启动。

from langchain.chat_models import ChatOpenAI
from langchain.chains import GraphCypherQAChain
from langchain.graphs import Neo4jGraph
graph = Neo4jGraph(
    url="bolt://localhost:7687", username="neo4j", password="pleaseletmein"
)

初始化数据库​

假设您的数据库是空的，您可以使用Cypher查询语言填充它。以下Cypher语句是幂等的，这意味着如果您运行它一次或多次，数据库信息将是相同的。

graph.query(
    """
MERGE (m:Movie {name:"Top Gun"})
WITH m
UNWIND ["Tom Cruise", "Val Kilmer", "Anthony Edwards", "Meg Ryan"] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)
    []

刷新图形模式信息​

如果数据库的模式发生更改，您可以刷新生成Cypher语句所需的模式信息。

graph.refresh_schema()
print(graph.get_schema)
    
            Node properties are the following:
            [{'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Movie'}, {'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Actor'}]
            Relationship properties are the following:
            []
            The relationships are the following:
            ['(:Actor)-[:ACTED_IN]->(:Movie)']

查询图形​

现在我们可以使用图形Cypher QA链来询问图形的问题

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True
)
chain.run("Who played in Top Gun?")
    
    
    > Entering new GraphCypherQAChain chain...
    Generated Cypher:
    MATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})
    RETURN a.name
    Full Context:
    [{'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}, {'a.name': 'Tom Cruise'}]
    
    > Finished chain.





    'Val Kilmer, Anthony Edwards, Meg Ryan, and Tom Cruise played in Top Gun.'

限制结果数量​

您可以使用top_k参数限制Cypher QA链的结果数量。 默认值为10。

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, top_k=2
)
chain.run("Who played in Top Gun?")
    
    
    > Entering new GraphCypherQAChain chain...
    Generated Cypher:
    MATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})
    RETURN a.name
    Full Context:
    [{'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}]
    
    > Finished chain.





    'Val Kilmer and Anthony Edwards played in Top Gun.'

返回中间结果​

您可以使用return_intermediate_steps参数从Cypher QA链返回中间步骤

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, return_intermediate_steps=True
)
result = chain("Who played in Top Gun?")
print(f"Intermediate steps: {result['intermediate_steps']}")
print(f"Final answer: {result['result']}")
    
    
    > Entering new GraphCypherQAChain chain...
    Generated Cypher:
    MATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})
    RETURN a.name
    Full Context:
    [{'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}, {'a.name': 'Tom Cruise'}]
    
    > Finished chain.
    Intermediate steps: [{'query': "MATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})\nRETURN a.name"}, {'context': [{'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}, {'a.name': 'Tom Cruise'}]}]
    Final answer: Val Kilmer, Anthony Edwards, Meg Ryan, and Tom Cruise played in Top Gun.

返回直接结果​

您可以使用return_direct参数从Cypher QA链返回直接结果

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, return_direct=True
)
chain.run("Who played in Top Gun?")
    
    
    > Entering new GraphCypherQAChain chain...
    Generated Cypher:
    MATCH (a:Actor)-[:ACTED_IN]->(m:Movie {name: 'Top Gun'})
    RETURN a.name
    
    > Finished chain.





    [{'a.name': 'Val Kilmer'},
     {'a.name': 'Anthony Edwards'},
     {'a.name': 'Meg Ryan'},
     {'a.name': 'Tom Cruise'}]