Neo4J

Neo4j 是由 Neo4j, Inc 开发的图数据库管理系统。

数据元素 Neo4j 存储的是节点、连接它们的边，以及节点和边的属性。其开发者将其描述为一个符合 ACID 的事务型数据库，具有原生的图存储与处理能力。Neo4j 以非开源的“社区版”形式提供，采用修改版的 GNU 通用公共许可证授权，而在线备份和高可用性扩展功能则采用闭源的商业许可证授权。Neo 还在闭源的商业条款下授权 Neo4j 使用这些扩展功能。

此笔记本展示了如何使用大语言模型（LLM）为图数据库提供自然语言接口，您可以使用 Cypher 查询语言对其进行查询。

Cypher 是一种声明式的图查询语言，可在属性图中实现富有表现力且高效的数据查询。

设置

您需要有一个正在运行的 Neo4j 实例。一种选择是在 Neo4j 的 Aura 云服务中创建一个免费的 Neo4j 数据库实例。您也可以使用Neo4j Desktop 应用程序在本地运行数据库，或通过运行 Docker 容器来启动。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/password \
    -e NEO4J_PLUGINS=\[\"apoc\"\]  \
    neo4j:latest

如果您使用的是 Docker 容器，则需要等待几秒钟，以便数据库启动。

from langchain_neo4j import GraphCypherQAChain, Neo4jGraph
from langchain_openai import ChatOpenAI

API 参考:图CypherQA链 |Neo4j图数据库 |ChatOpenAI

graph = Neo4jGraph(url="bolt://localhost:7687", username="neo4j", password="password")

本指南默认使用 OpenAI 模型。

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

填充数据库

假设您的数据库为空，您可以使用Cypher查询语言来填充它。以下Cypher语句是幂等的，这意味着无论您运行一次还是多次，数据库中的信息都将保持不变。

graph.query(
    """
MERGE (m:Movie {name:"Top Gun", runtime: 120})
WITH m
UNWIND ["Tom Cruise", "Val Kilmer", "Anthony Edwards", "Meg Ryan"] AS actor
MERGE (a:Actor {name:actor})
MERGE (a)-[:ACTED_IN]->(m)
"""
)

[]

刷新图谱模式信息

如果数据库的模式发生变化，您可以刷新生成Cypher语句所需的模式信息。

graph.refresh_schema()

print(graph.schema)

Node properties:
Movie {runtime: INTEGER, name: STRING}
Actor {name: STRING}
Relationship properties:

The relationships:
(:Actor)-[:ACTED_IN]->(:Movie)

增强的模式信息

选择增强型模式版本后，系统将自动扫描数据库中的示例值，并计算一些分布统计信息。例如，如果某个节点属性的唯一值少于10个，我们将在模式中返回所有可能的值；否则，每个节点和关系属性仅返回一个示例值。

enhanced_graph = Neo4jGraph(
    url="bolt://localhost:7687",
    username="neo4j",
    password="password",
    enhanced_schema=True,
)
print(enhanced_graph.schema)

Node properties:
- **Movie**
  - `runtime`: INTEGER Min: 120, Max: 120
  - `name`: STRING Available options: ['Top Gun']
- **Actor**
  - `name`: STRING Available options: ['Tom Cruise', 'Val Kilmer', 'Anthony Edwards', 'Meg Ryan']
Relationship properties:

The relationships:
(:Actor)-[:ACTED_IN]->(:Movie)

查询图谱

我们现在可以使用图谱Cypher问答链来向图谱提问

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, allow_dangerous_requests=True
)

chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.'}

限制结果数量

您可以通过使用 top_k 参数来限制 Cypher QA 链返回的结果数量。默认值为 10。

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    top_k=2,
    allow_dangerous_requests=True,
)

chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer 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,
    allow_dangerous_requests=True,
)

result = chain.invoke({"query": "Who played in Top Gun?"})
print(f"Intermediate steps: {result['intermediate_steps']}")
print(f"Final answer: {result['result']}")

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m
Intermediate steps: [{'query': "MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)\nWHERE m.name = 'Top Gun'\nRETURN a.name"}, {'context': [{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]}]
Final answer: Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.

返回直接结果

您可以使用 return_direct 参数从Cypher QA链直接返回结果

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    return_direct=True,
    allow_dangerous_requests=True,
)

chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': [{'a.name': 'Tom Cruise'},
  {'a.name': 'Val Kilmer'},
  {'a.name': 'Anthony Edwards'},
  {'a.name': 'Meg Ryan'}]}

在Cypher生成提示中添加示例

您可以定义希望LLM为特定问题生成的Cypher语句

from langchain_core.prompts.prompt import PromptTemplate

CYPHER_GENERATION_TEMPLATE = """Task:Generate Cypher statement to query a graph database.
Instructions:
Use only the provided relationship types and properties in the schema.
Do not use any other relationship types or properties that are not provided.
Schema:
{schema}
Note: Do not include any explanations or apologies in your responses.
Do not respond to any questions that might ask anything else than for you to construct a Cypher statement.
Do not include any text except the generated Cypher statement.
Examples: Here are a few examples of generated Cypher statements for particular questions:
# How many people played in Top Gun?
MATCH (m:Movie {{name:"Top Gun"}})<-[:ACTED_IN]-()
RETURN count(*) AS numberOfActors

The question is:
{question}"""

CYPHER_GENERATION_PROMPT = PromptTemplate(
    input_variables=["schema", "question"], template=CYPHER_GENERATION_TEMPLATE
)

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    cypher_prompt=CYPHER_GENERATION_PROMPT,
    allow_dangerous_requests=True,
)

API 参考:提示模板

chain.invoke({"query": "How many people played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (m:Movie {name:"Top Gun"})<-[:ACTED_IN]-()
RETURN count(*) AS numberOfActors[0m
Full Context:
[32;1m[1;3m[{'numberOfActors': 4}][0m

[1m> Finished chain.[0m

{'query': 'How many people played in Top Gun?',
 'result': 'There were 4 actors in Top Gun.'}

为 Cypher 和答案生成使用独立的 LLM

您可以使用 cypher_llm 和 qa_llm 参数来定义不同的大语言模型（llms）

chain = GraphCypherQAChain.from_llm(
    graph=graph,
    cypher_llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo"),
    qa_llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k"),
    verbose=True,
    allow_dangerous_requests=True,
)

chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.'}

忽略指定的节点和关系类型

您可以使用 include_types 或 exclude_types 在生成 Cypher 语句时忽略图结构的某些部分。

chain = GraphCypherQAChain.from_llm(
    graph=graph,
    cypher_llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo"),
    qa_llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k"),
    verbose=True,
    exclude_types=["Movie"],
    allow_dangerous_requests=True,
)

# Inspect graph schema
print(chain.graph_schema)

Node properties are the following:
Actor {name: STRING}
Relationship properties are the following:

The relationships are the following:

验证生成的Cypher语句

您可以使用 validate_cypher 参数来验证和纠正生成的 Cypher 语句中的关系方向

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

chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.'}

将数据库结果中的上下文作为工具/函数输出提供

您可以使用 use_function_response 参数将数据库结果中的上下文作为工具/函数输出传递给大语言模型（LLM）。此方法通过让LLM更紧密地遵循所提供的上下文，提高回答的准确性和相关性。 您需要使用支持原生函数调用的LLM才能使用此功能。

chain = GraphCypherQAChain.from_llm(
    llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo"),
    graph=graph,
    verbose=True,
    use_function_response=True,
    allow_dangerous_requests=True,
)
chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': 'The main actors in Top Gun are Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan.'}

使用函数响应功能时，可以通过提供 function_response_system 来提供自定义系统消息，以指示模型如何生成答案。

请注意，当使用 use_function_response 时，qa_prompt 将不起任何作用

chain = GraphCypherQAChain.from_llm(
    llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo"),
    graph=graph,
    verbose=True,
    use_function_response=True,
    function_response_system="Respond as a pirate!",
    allow_dangerous_requests=True,
)
chain.invoke({"query": "Who played in Top Gun?"})

[1m> Entering new GraphCypherQAChain chain...[0m
Generated Cypher:
[32;1m[1;3mMATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name[0m
Full Context:
[32;1m[1;3m[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}][0m

[1m> Finished chain.[0m

{'query': 'Who played in Top Gun?',
 'result': "Arrr matey! In the film Top Gun, ye be seein' Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan sailin' the high seas of the sky! Aye, they be a fine crew of actors, they be!"}

设置​

填充数据库​

刷新图谱模式信息​

增强的模式信息​

查询图谱​

限制结果数量​

返回中间结果​

返回直接结果​

在Cypher生成提示中添加示例​

为 Cypher 和答案生成使用独立的 LLM​

忽略指定的节点和关系类型​

验证生成的Cypher语句​

将数据库结果中的上下文作为工具/函数输出提供​

设置