使用自然语言接口与Memgraph数据库交互：从入门到精通

本文链接：https://blog.csdn.net/cgsayuclv/article/details/142756803

## 引言

随着图数据库在大数据分析中的普及，利用自然语言处理技术简化数据库查询过程成为了开发者关注的焦点。本文将介绍如何使用大语言模型（LLM）与Memgraph数据库交互，通过自然语言接口高效地进行数据查询。

## 主要内容

### 设置环境

要完成这篇教程，你需要安装Docker和Python 3.x，并确保Memgraph实例正在运行。快速启动Memgraph的方法如下：

**Linux/MacOS:**
```bash
curl https://install.memgraph.com | sh

Windows:

iwr https://windows.memgraph.com | iex

这些命令会下载Docker Compose文件并启动memgraph-mage和memgraph-lab服务。

安装所需包

使用pip安装必要的Python包：

pip install langchain langchain-openai neo4j gqlalchemy --user

建立数据库连接

以下是通过GQLAlchemy连接Memgraph数据库的代码示例：

from gqlalchemy import Memgraph

memgraph = Memgraph(host="127.0.0.1", port=7687)

填充数据库

使用Cypher语言填充你的数据库：

query = """
    MERGE (g:Game {name: "Baldur's Gate 3"})
    WITH g, ["PlayStation 5", "Mac OS", "Windows", "Xbox Series X/S"] AS platforms,
            ["Adventure", "Role-Playing Game", "Strategy"] AS genres
    FOREACH (platform IN platforms |
        MERGE (p:Platform {name: platform})
        MERGE (g)-[:AVAILABLE_ON]->(p)
    )
    FOREACH (genre IN genres |
        MERGE (gn:Genre {name: genre})
        MERGE (g)-[:HAS_GENRE]->(gn)
    )
    MERGE (p:Publisher {name: "Larian Studios"})
    MERGE (g)-[:PUBLISHED_BY]->(p);
"""

memgraph.execute(query)

查询数据库

设置环境变量以配置OpenAI API密钥：

import os

os.environ["OPENAI_API_KEY"] = "your-key-here"

创建图链进行问答：

from langchain.chains import GraphCypherQAChain
from langchain_community.graphs import MemgraphGraph
from langchain_openai import ChatOpenAI

graph = MemgraphGraph(url="bolt://localhost:7687", username="", password="")
chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0), graph=graph, verbose=True, model_name="gpt-3.5-turbo"
)

response = chain.run("Which platforms is Baldur's Gate 3 available on?")
print(response)

常见问题和解决方案

数据查询不匹配

遇到用户查询与存储数据不匹配时，可以通过提示优化来解决。这包括修改QA链的初始Cypher提示：

from langchain_core.prompts 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.
...
"""

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

chain = GraphCypherQAChain.from_llm(
    ChatOpenAI(temperature=0),
    cypher_prompt=CYPHER_GENERATION_PROMPT,
    graph=graph,
    verbose=True,
    model_name="gpt-3.5-turbo",
)

response = chain.run("Is Baldur's Gate 3 available on PS5?")
print(response)