Azure Cosmos DB for Apache Gremlin
Azure Cosmos DB for Apache Gremlin 是一种图数据库服务,可用于存储拥有数十亿顶点和边的海量图。您可以用毫秒级的延迟查询图,并轻松地演进图结构。
Gremlin 是由
Apache Software Foundation的Apache TinkerPop开发的一种图遍历语言和虚拟机。
本笔记本展示了如何使用 LLM 为图数据库提供自然语言接口,该数据库可以使用 Gremlin 查询语言进行查询。
设置
安装一个库:
!pip3 install gremlinpython
您需要一个 Azure CosmosDB Graph 数据库实例。一种选择是在 Azure 中创建一个免费的 CosmosDB Graph 数据库实例。
创建 Cosmos DB 帐户和 Graph 时,请使用 /type 作为分区键。
cosmosdb_name = "mycosmosdb"
cosmosdb_db_id = "graphtesting"
cosmosdb_db_graph_id = "mygraph"
cosmosdb_access_Key = "longstring=="
import nest_asyncio
from langchain_community.chains.graph_qa.gremlin import GremlinQAChain
from langchain_community.graphs import GremlinGraph
from langchain_community.graphs.graph_document import GraphDocument, Node, Relationship
from langchain_core.documents import Document
from langchain_openai import AzureChatOpenAI
API Reference:GremlinQAChain | GremlinGraph | GraphDocument | Node | Relationship | Document | AzureChatOpenAI
graph = GremlinGraph(
url=f"wss://{cosmosdb_name}.gremlin.cosmos.azure.com:443/",
username=f"/dbs/{cosmosdb_db_id}/colls/{cosmosdb_db_graph_id}",
password=cosmosdb_access_Key,
)
填充数据库
假设您的数据库为空,您可以使用 GraphDocuments 来填充它。
对于 Gremlin,请始终为每个节点添加名为 'label' 的属性。 如果没有设置 label,则使用 Node.type 作为 label。 对于 cosmos,使用 natural id's 是有意义的,因为它们在 graph explorer 中是可见的。
source_doc = Document(
page_content="Matrix is a movie where Keanu Reeves, Laurence Fishburne and Carrie-Anne Moss acted."
)
movie = Node(id="The Matrix", properties={"label": "movie", "title": "The Matrix"})
actor1 = Node(id="Keanu Reeves", properties={"label": "actor", "name": "Keanu Reeves"})
actor2 = Node(
id="Laurence Fishburne", properties={"label": "actor", "name": "Laurence Fishburne"}
)
actor3 = Node(
id="Carrie-Anne Moss", properties={"label": "actor", "name": "Carrie-Anne Moss"}
)
rel1 = Relationship(
id=5, type="ActedIn", source=actor1, target=movie, properties={"label": "ActedIn"}
)
rel2 = Relationship(
id=6, type="ActedIn", source=actor2, target=movie, properties={"label": "ActedIn"}
)
rel3 = Relationship(
id=7, type="ActedIn", source=actor3, target=movie, properties={"label": "ActedIn"}
)
rel4 = Relationship(
id=8,
type="Starring",
source=movie,
target=actor1,
properties={"label": "Strarring"},
)
rel5 = Relationship(
id=9,
type="Starring",
source=movie,
target=actor2,
properties={"label": "Strarring"},
)
rel6 = Relationship(
id=10,
type="Straring",
source=movie,
target=actor3,
properties={"label": "Strarring"},
)
graph_doc = GraphDocument(
nodes=[movie, actor1, actor2, actor3],
relationships=[rel1, rel2, rel3, rel4, rel5, rel6],
source=source_doc,
)
# The underlying python-gremlin has a problem when running in notebook
# The following line is a workaround to fix the problem
nest_asyncio.apply()
# Add the document to the CosmosDB graph.
graph.add_graph_documents([graph_doc])
刷新图谱架构信息
如果数据库的架构发生变化(更新后),您可以刷新架构信息。
graph.refresh_schema()
print(graph.schema)
查询图
我们现在可以使用 gremlin QA 链来对图提出问题
chain = GremlinQAChain.from_llm(
AzureChatOpenAI(
temperature=0,
azure_deployment="gpt-4-turbo",
),
graph=graph,
verbose=True,
)
chain.invoke("Who played in The Matrix?")
chain.run("How many people played in The Matrix?")