如何构建知识图谱

在本指南中，我们将介绍基于非结构化文本构建知识图谱的基本方法。构建的图谱可以作为 RAG 应用程序中的知识库使用。

⚠️ 安全注意事项 ⚠️

构建知识图谱需要执行对数据库的写入访问权限。这样做存在内在风险。在导入数据之前，请务必验证和确认数据。有关一般安全最佳实践的更多信息，请参阅此处。

架构

从文本构建知识图谱的高级步骤是

从文本中提取结构化信息：模型用于从文本中提取结构化图信息。
存储到图数据库：将提取的结构化图信息存储到图数据库中，以支持下游 RAG 应用程序

设置

首先，获取所需的软件包并设置环境变量。在本示例中，我们将使用 Neo4j 图数据库。

%pip install --upgrade --quiet  langchain langchain-neo4j langchain-openai langchain-experimental neo4j

[1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m A new release of pip is available: [0m[31;49m24.0[0m[39;49m -> [0m[32;49m24.3.1[0m
[1m[[0m[34;49mnotice[0m[1;39;49m][0m[39;49m To update, run: [0m[32;49mpip install --upgrade pip[0m
Note: you may need to restart the kernel to use updated packages.

在本指南中，我们默认使用 OpenAI 模型。

import getpass
import os

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

# Uncomment the below to use LangSmith. Not required.
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()
# os.environ["LANGSMITH_TRACING"] = "true"

 ········

接下来，我们需要定义 Neo4j 凭据和连接。按照这些安装步骤设置 Neo4j 数据库。

import os

from langchain_neo4j import Neo4jGraph

os.environ["NEO4J_URI"] = "bolt://#:7687"
os.environ["NEO4J_USERNAME"] = "neo4j"
os.environ["NEO4J_PASSWORD"] = "password"

graph = Neo4jGraph(refresh_schema=False)

API 参考：Neo4jGraph

LLM 图转换器

从文本中提取图数据可以将非结构化信息转换为结构化格式，从而更深入地了解复杂的关系和模式，并更有效地导航。LLMGraphTransformer 通过利用 LLM 解析和分类实体及其关系，将文本文档转换为结构化图文档。LLM 模型的选择通过确定提取的图数据的准确性和细微差别，显著影响输出。

import os

from langchain_experimental.graph_transformers import LLMGraphTransformer
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0, model_name="gpt-4-turbo")

llm_transformer = LLMGraphTransformer(llm=llm)

API 参考：LLMGraphTransformer | ChatOpenAI

现在我们可以传入示例文本并检查结果。

from langchain_core.documents import Document

text = """
Marie Curie, born in 1867, was a Polish and naturalised-French physicist and chemist who conducted pioneering research on radioactivity.
She was the first woman to win a Nobel Prize, the first person to win a Nobel Prize twice, and the only person to win a Nobel Prize in two scientific fields.
Her husband, Pierre Curie, was a co-winner of her first Nobel Prize, making them the first-ever married couple to win the Nobel Prize and launching the Curie family legacy of five Nobel Prizes.
She was, in 1906, the first woman to become a professor at the University of Paris.
"""
documents = [Document(page_content=text)]
graph_documents = llm_transformer.convert_to_graph_documents(documents)
print(f"Nodes:{graph_documents[0].nodes}")
print(f"Relationships:{graph_documents[0].relationships}")

API 参考：Document

Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]
Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='MARRIED', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='PROFESSOR', properties={})]

查看下图以更好地理解生成的知识图谱的结构。

请注意，由于我们使用 LLM，因此图谱构建过程是非确定性的。因此，每次执行可能会得到略有不同的结果。

此外，您可以灵活地根据您的要求定义要提取的特定类型的节点和关系。

llm_transformer_filtered = LLMGraphTransformer(
    llm=llm,
    allowed_nodes=["Person", "Country", "Organization"],
    allowed_relationships=["NATIONALITY", "LOCATED_IN", "WORKED_AT", "SPOUSE"],
)
graph_documents_filtered = llm_transformer_filtered.convert_to_graph_documents(
    documents
)
print(f"Nodes:{graph_documents_filtered[0].nodes}")
print(f"Relationships:{graph_documents_filtered[0].relationships}")

Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]
Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]

为了更精确地定义图谱模式，请考虑对关系使用三元组方法。在这种方法中，每个元组包含三个元素：源节点、关系类型和目标节点。

allowed_relationships = [
    ("Person", "SPOUSE", "Person"),
    ("Person", "NATIONALITY", "Country"),
    ("Person", "WORKED_AT", "Organization"),
]

llm_transformer_tuple = LLMGraphTransformer(
    llm=llm,
    allowed_nodes=["Person", "Country", "Organization"],
    allowed_relationships=allowed_relationships,
)
graph_documents_filtered = llm_transformer_tuple.convert_to_graph_documents(documents)
print(f"Nodes:{graph_documents_filtered[0].nodes}")
print(f"Relationships:{graph_documents_filtered[0].relationships}")

Nodes:[Node(id='Marie Curie', type='Person', properties={}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={})]
Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]

为了更好地理解生成的图谱，我们可以再次对其进行可视化。

node_properties 参数启用节点属性的提取，从而可以创建更详细的图谱。当设置为 True 时，LLM 会自主识别和提取相关的节点属性。相反，如果 node_properties 定义为字符串列表，则 LLM 会仅从文本中选择性地检索指定的属性。

llm_transformer_props = LLMGraphTransformer(
    llm=llm,
    allowed_nodes=["Person", "Country", "Organization"],
    allowed_relationships=["NATIONALITY", "LOCATED_IN", "WORKED_AT", "SPOUSE"],
    node_properties=["born_year"],
)
graph_documents_props = llm_transformer_props.convert_to_graph_documents(documents)
print(f"Nodes:{graph_documents_props[0].nodes}")
print(f"Relationships:{graph_documents_props[0].relationships}")

Nodes:[Node(id='Marie Curie', type='Person', properties={'born_year': '1867'}), Node(id='Pierre Curie', type='Person', properties={}), Node(id='University Of Paris', type='Organization', properties={}), Node(id='Poland', type='Country', properties={}), Node(id='France', type='Country', properties={})]
Relationships:[Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Poland', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='France', type='Country', properties={}), type='NATIONALITY', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='Pierre Curie', type='Person', properties={}), type='SPOUSE', properties={}), Relationship(source=Node(id='Marie Curie', type='Person', properties={}), target=Node(id='University Of Paris', type='Organization', properties={}), type='WORKED_AT', properties={})]

存储到图数据库

可以使用 add_graph_documents 方法将生成的图文档存储到图数据库中。

graph.add_graph_documents(graph_documents_props)

大多数图数据库都支持索引以优化数据导入和检索。由于我们可能不知道所有节点标签，因此我们可以通过使用 baseEntityLabel 参数向每个节点添加辅助基本标签来处理此问题。

graph.add_graph_documents(graph_documents, baseEntityLabel=True)

结果将如下所示

最后一个选项是也导入提取的节点和关系的源文档。此方法使我们能够跟踪每个实体出现在哪些文档中。

graph.add_graph_documents(graph_documents, include_source=True)

图谱将具有以下结构

在此可视化中，源文档以蓝色突出显示，从中提取的所有实体都通过 MENTIONS 关系连接。

⚠️ 安全注意事项 ⚠️​

架构​

设置​

LLM 图转换器​

存储到图数据库​

此页内容是否对您有帮助？

⚠️ 安全注意事项 ⚠️

架构

设置

LLM 图转换器

存储到图数据库