Skip to main content


NebulaGraph is an open-source, distributed, scalable, lightning-fast graph database built for super large-scale graphs with milliseconds of latency. It uses the nGQL graph query language.

nGQL is a declarative graph query language for NebulaGraph. It allows expressive and efficient graph patterns. nGQL is designed for both developers and operations professionals. nGQL is an SQL-like query language.

This notebook shows how to use LLMs to provide a natural language interface to NebulaGraph database.

Setting up

You can start the NebulaGraph cluster as a Docker container by running the following script:

curl -fsSL | bash

Other options are:

Once the cluster is running, we could create the SPACE and SCHEMA for the database.

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

# connect ngql jupyter extension to nebulagraph
%ngql --address --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;

Create the schema, for full dataset, refer here.

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

Wait for schema creation to complete, then we can insert some data.

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(

Refresh graph schema information

If the schema of database changes, you can refresh the schema information needed to generate nGQL statements.

# graph.refresh_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)']

Querying the graph

We can now use the graph cypher QA chain to ask question of the graph

chain = NebulaGraphQAChain.from_llm(
ChatOpenAI(temperature=0), graph=graph, verbose=True
)"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:
{'': ['Al Pacino']}

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

Help us out by providing feedback on this documentation page: