> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Neo4j 集成

> 使用 LangChain Python 集成 Neo4j。

> [Neo4j](https://neo4j.com/docs/getting-started/) 是由 `Neo4j, Inc`.

> `Neo4j` 存储的数据元素包括节点、连接节点的边以及节点和边的属性。开发者将其描述为一个符合 ACID 标准的事务型数据库，具有原生图存储和处理能力。`Neo4j` 提供非开源的"社区版"（使用修改版 GNU 通用公共许可证授权），在线备份和高可用性扩展则使用闭源商业许可证授权。

> 本 notebook 展示如何使用 LLM 为图数据库提供自然语言接口，你可以使用 `Cypher` 查询语言来查询该数据库。

> [Cypher](https://en.wikipedia.org/wiki/Cypher_\(query_language\)) 是一种声明式图查询语言，允许在属性图中进行富有表达力且高效的数据查询。

## 设置

你需要一个正在运行的 `Neo4j` instance. One option is to create a [free Neo4j database instance in their Aura cloud service](https://neo4j.com/cloud/platform/aura-graph-database/). 你也可以使用以下方式在本地运行数据库： [Neo4j Desktop application](https://neo4j.com/download/), or running a docker container.
你可以通过执行以下脚本运行本地 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
```

如果使用 docker 容器，你需要等待几秒钟让数据库启动。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_neo4j import GraphCypherQAChain, Neo4jGraph
from langchain_openai import ChatOpenAI
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph = Neo4jGraph(url="bolt://localhost:7687", username="neo4j", password="password")
```

本指南中我们默认使用 OpenAI 模型。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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

假设你的数据库为空，你可以使用 Cypher 查询语言填充数据。 以下 Cypher 语句是幂等的，这意味着无论运行一次还是多次，数据库信息都是相同的。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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)
"""
)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[]
```

## 刷新图 Schema 信息

如果数据库的 Schema 发生变化，你可以刷新生成 Cypher 语句所需的 Schema 信息。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
graph.refresh_schema()
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
print(graph.schema)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
Node properties:
Movie {runtime: INTEGER, name: STRING}
Actor {name: STRING}
Relationship properties:

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

## 增强 Schema 信息

选择增强 Schema 版本使系统能够自动扫描数据库中的示例值 并计算一些分布指标。 例如, if a node property has less than 10 distinct values, we return all possible values in the schema. 否则，每个节点和关系属性仅返回一个示例值。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
enhanced_graph = Neo4jGraph(
    url="bolt://localhost:7687",
    username="neo4j",
    password="password",
    enhanced_schema=True,
)
print(enhanced_graph.schema)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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

我们现在可以使用 graph cypher QA chain 来查询图

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, allow_dangerous_requests=True
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "Who played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'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

你可以使用 `top_k` 参数来限制 Cypher QA Chain 返回的结果数量。
默认值为 10。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    top_k=2,
    allow_dangerous_requests=True,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "Who played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer played in Top Gun.'}
```

## 返回中间结果

你可以使用 `return_intermediate_steps` 参数从 Cypher QA Chain 返回中间步骤

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    return_intermediate_steps=True,
    allow_dangerous_requests=True,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
result = chain.invoke({"query": "Who played in Top Gun?"})
print(f"Intermediate steps: {result['intermediate_steps']}")
print(f"Final answer: {result['result']}")
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
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

你可以使用 `return_direct` 参数从 Cypher QA Chain 返回直接结果

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    graph=graph,
    verbose=True,
    return_direct=True,
    allow_dangerous_requests=True,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "Who played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'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 生成提示词中添加示例

你可以定义希望 LLM 为特定问题生成的 Cypher 语句

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "How many people played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (m:Movie {name:"Top Gun"})<-[:ACTED_IN]-()
RETURN count(*) AS numberOfActors
Full Context:
[{'numberOfActors': 4}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'query': 'How many people played in Top Gun?',
 'result': 'There were 4 actors in Top Gun.'}
```

## 使用不同的 LLM 进行 Cypher 和答案生成

你可以使用 `cypher_llm` 和 `qa_llm` 参数来定义不同的 LLM

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "Who played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'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

你可以使用 `include_types` 或 `exclude_types` 来在生成 Cypher 语句时忽略部分图 Schema。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# 检查图 Schema
print(chain.graph_schema)
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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

你可以使用 `validate_cypher` 参数来验证和修正生成的 Cypher 语句中的关系方向

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain = GraphCypherQAChain.from_llm(
    llm=ChatOpenAI(temperature=0, model="gpt-3.5-turbo"),
    graph=graph,
    verbose=True,
    validate_cypher=True,
    allow_dangerous_requests=True,
)
```

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
chain.invoke({"query": "Who played in Top Gun?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'query': 'Who played in Top Gun?',
 'result': 'Tom Cruise, Val Kilmer, Anthony Edwards, and Meg Ryan played in Top Gun.'}
```

## 将数据库结果作为工具/函数输出提供上下文

你可以使用 `use_function_response` 参数将数据库结果作为工具/函数输出传递给 LLM。 此方法提高了响应的准确性和相关性 of an answer as the LLM follows the provided context more closely.
*你需要使用支持原生函数调用的 LLM 来使用此功能*。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'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，你可以提供自定义系统消息 by providing `function_response_system` to instruct the model on how to generate answers.

*注意使用 `use_function_response` 时 `qa_prompt` 将不起作用*

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
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?"})
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
> Entering new GraphCypherQAChain chain...
Generated Cypher:
MATCH (a:Actor)-[:ACTED_IN]->(m:Movie)
WHERE m.name = 'Top Gun'
RETURN a.name
Full Context:
[{'a.name': 'Tom Cruise'}, {'a.name': 'Val Kilmer'}, {'a.name': 'Anthony Edwards'}, {'a.name': 'Meg Ryan'}]

> Finished chain.
```

```text theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
{'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!"}
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/graphs/neo4j_cypher.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>