跳转到主要内容

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。然后,可以将构造的图用作 RAG 应用程序中的知识库。

⚠️ 安全提示 ⚠️

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。请确保在导入数据之前对其进行验证和确认。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步骤大致如下:

  1. 从文本中提取结构化信息:使用模型从文本中提取结构化图信息。
  2. 存储到图数据库中:将提取的结构化图信息存储到图数据库中,以便支持下游的 RAG 应用。

设置

首先,获取所需的包并设置环境变量。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

[notice] A new release of pip is available: 24.0 -> 24.3.1
[notice] To update, run: pip install --upgrade pip
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["LANGCHAIN_API_KEY"] = getpass.getpass()
# os.environ["LANGCHAIN_TRACING_V2"] = "true"
 ········

接下来,我们需要定义 Neo4j 凭据和连接。请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://127.0.0.1:7687"
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,从而更深入地了解并更有效地浏览复杂的关联和模式。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 模型的选择通过决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)

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={})]

查看以下图像,以更好地理解生成的知识图的结构。

graph_construction1.png

请注意,由于我们正在使用 LLM,因此图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={})]

要更精确地定义图模式,请考虑使用关系的三元组方法。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,我们可以再次将其可视化。

graph_construction2.png

node_properties 参数允许提取节点属性,从而创建更详细的图。当设置为 True 时,LLM 会自主识别并提取相关的节点属性。相反,如果将 node_properties 定义为字符串列表,则 LLM 会有选择地仅从文本中检索指定的属性。

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来优化数据导入和检索。由于我们可能无法预先知道所有节点标签,我们可以使用 baseEntityLabel 参数为每个节点添加一个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

graph_construction3.png

最后一个选项是导入提取的节点和关系的源文档。此方法允许我们跟踪每个实体出现在哪些文档中。

graph.add_graph_documents(graph_documents, include_source=True)

图将具有以下结构

graph_construction4.png

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


此页面有帮助吗?