Skip to main content
Open In ColabOpen on GitHub

NebulaGraph

NebulaGraph 是一个开源的、分布式的、可扩展的、极速的图数据库,专为超大规模图设计,具有毫秒级的延迟。它使用 nGQL 图查询语言。

nGQL 是一种用于 NebulaGraph 的声明式图查询语言。它允许表达性强且高效的图模式。nGQL 专为开发人员和运维专业人员设计。nGQL 是一种类似 SQL 的查询语言。

本笔记本展示了如何使用LLMs为NebulaGraph数据库提供自然语言接口。

设置

你可以通过运行以下脚本来启动NebulaGraph集群作为Docker容器:

curl -fsSL nebula-up.siwei.io/install.sh | bash

其他选项包括:

一旦集群运行起来,我们可以为数据库创建SPACESCHEMA

%pip install --upgrade --quiet  ipython-ngql
%load_ext ngql

# connect ngql jupyter extension to nebulagraph
%ngql --address 127.0.0.1 --port 9669 --user root --password nebula
# create a new space
%ngql CREATE SPACE IF NOT EXISTS langchain(partition_num=1, replica_factor=1, vid_type=fixed_string(128));
# Wait for a few seconds for the space to be created.
%ngql USE langchain;

创建模式,完整数据集请参考这里

%%ngql
CREATE TAG IF NOT EXISTS movie(name string);
CREATE TAG IF NOT EXISTS person(name string, birthdate string);
CREATE EDGE IF NOT EXISTS acted_in();
CREATE TAG INDEX IF NOT EXISTS person_index ON person(name(128));
CREATE TAG INDEX IF NOT EXISTS movie_index ON movie(name(128));

等待模式创建完成,然后我们可以插入一些数据。

%%ngql
INSERT VERTEX person(name, birthdate) VALUES "Al Pacino":("Al Pacino", "1940-04-25");
INSERT VERTEX movie(name) VALUES "The Godfather II":("The Godfather II");
INSERT VERTEX movie(name) VALUES "The Godfather Coda: The Death of Michael Corleone":("The Godfather Coda: The Death of Michael Corleone");
INSERT EDGE acted_in() VALUES "Al Pacino"->"The Godfather II":();
INSERT EDGE acted_in() VALUES "Al Pacino"->"The Godfather Coda: The Death of Michael Corleone":();
from langchain.chains import NebulaGraphQAChain
from langchain_community.graphs import NebulaGraph
from langchain_openai import ChatOpenAI
graph = NebulaGraph(
space="langchain",
username="root",
password="nebula",
address="127.0.0.1",
port=9669,
session_pool_size=30,
)

刷新图模式信息

如果数据库的模式发生变化,您可以刷新生成nGQL语句所需的模式信息。

# graph.refresh_schema()
print(graph.get_schema)
Node properties: [{'tag': 'movie', 'properties': [('name', 'string')]}, {'tag': 'person', 'properties': [('name', 'string'), ('birthdate', 'string')]}]
Edge properties: [{'edge': 'acted_in', 'properties': []}]
Relationships: ['(:person)-[:acted_in]->(:movie)']

查询图

我们现在可以使用图Cypher QA链来询问图的问题

chain = NebulaGraphQAChain.from_llm(
ChatOpenAI(temperature=0), graph=graph, verbose=True
)
chain.run("Who played in The Godfather II?")


> Entering new NebulaGraphQAChain chain...
Generated nGQL:
MATCH (p:`person`)-[:acted_in]->(m:`movie`) WHERE m.`movie`.`name` == 'The Godfather II'
RETURN p.`person`.`name`
Full Context:
{'p.person.name': ['Al Pacino']}

> Finished chain.
'Al Pacino played in The Godfather II.'

这个页面有帮助吗?