如何构建知识图谱

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

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"

import os

from langchain_neo4j import Neo4jGraph

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

graph = Neo4jGraph(refresh_schema=False)

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)

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}")

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}")

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}")

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}")

graph.add_graph_documents(graph_documents_props)

graph.add_graph_documents(graph_documents, baseEntityLabel=True)

graph.add_graph_documents(graph_documents, include_source=True)