Neo4j 向量索引

Neo4j 是一个开源图数据库，具有对向量相似性搜索的集成支持

它支持

近似最近邻搜索
欧几里得相似性和余弦相似性
结合向量和关键字搜索的混合搜索

此笔记本演示如何使用 Neo4j 向量索引（Neo4jVector）。

# Pip install necessary package
%pip install --upgrade --quiet  neo4j
%pip install --upgrade --quiet  langchain-openai langchain-community
%pip install --upgrade --quiet  tiktoken

我们希望使用OpenAIEmbeddings，因此我们必须获取 OpenAI API 密钥。

import getpass
import os

if "OPENAI_API_KEY" not in os.environ:
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

OpenAI API Key: ········

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import Neo4jVector
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

API 参考：TextLoader | Neo4jVector | Document | OpenAIEmbeddings | CharacterTextSplitter

loader = TextLoader("../../how_to/state_of_the_union.txt")

documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

embeddings = OpenAIEmbeddings()

# Neo4jVector requires the Neo4j database credentials

url = "bolt://localhost:7687"
username = "neo4j"
password = "password"

# You can also use environment variables instead of directly passing named parameters
# os.environ["NEO4J_URI"] = "bolt://localhost:7687"
# os.environ["NEO4J_USERNAME"] = "neo4j"
# os.environ["NEO4J_PASSWORD"] = "pleaseletmein"

使用余弦距离的相似性搜索（默认）

# The Neo4jVector Module will connect to Neo4j and create a vector index if needed.

db = Neo4jVector.from_documents(
    docs, OpenAIEmbeddings(), url=url, username=username, password=password
)

query = "What did the president say about Ketanji Brown Jackson"
docs_with_score = db.similarity_search_with_score(query, k=2)

for doc, score in docs_with_score:
    print("-" * 80)
    print("Score: ", score)
    print(doc.page_content)
    print("-" * 80)

--------------------------------------------------------------------------------
Score:  0.9076391458511353
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. 

Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. 

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
--------------------------------------------------------------------------------
--------------------------------------------------------------------------------
Score:  0.8912242650985718
A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. 

And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. 

We can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  

We’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  

We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. 

We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.
--------------------------------------------------------------------------------

使用向量存储

上面，我们从头创建了一个向量存储。但是，通常我们希望使用现有的向量存储。为此，我们可以直接初始化它。

index_name = "vector"  # default index name

store = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=index_name,
)

我们还可以使用from_existing_graph方法从现有图形初始化向量存储。此方法从数据库中提取相关的文本信息，并计算并将文本嵌入存储回数据库。

# First we create sample data in graph
store.query(
    "CREATE (p:Person {name: 'Tomaz', location:'Slovenia', hobby:'Bicycle', age: 33})"
)

[]

# Now we initialize from existing graph
existing_graph = Neo4jVector.from_existing_graph(
    embedding=OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    node_label="Person",
    text_node_properties=["name", "location"],
    embedding_node_property="embedding",
)
result = existing_graph.similarity_search("Slovenia", k=1)

result[0]

Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})

Neo4j 还支持关系向量索引，其中嵌入存储为关系属性并进行索引。关系向量索引无法通过 LangChain 填充，但您可以将其连接到现有的关系向量索引。

# First we create sample data and index in graph
store.query(
    "MERGE (p:Person {name: 'Tomaz'}) "
    "MERGE (p1:Person {name:'Leann'}) "
    "MERGE (p1)-[:FRIEND {text:'example text', embedding:$embedding}]->(p2)",
    params={"embedding": OpenAIEmbeddings().embed_query("example text")},
)
# Create a vector index
relationship_index = "relationship_vector"
store.query(
    """
CREATE VECTOR INDEX $relationship_index
IF NOT EXISTS
FOR ()-[r:FRIEND]-() ON (r.embedding)
OPTIONS {indexConfig: {
 `vector.dimensions`: 1536,
 `vector.similarity_function`: 'cosine'
}}
""",
    params={"relationship_index": relationship_index},
)

[]

relationship_vector = Neo4jVector.from_existing_relationship_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=relationship_index,
    text_node_property="text",
)
relationship_vector.similarity_search("Example")

[Document(page_content='example text')]

元数据过滤

Neo4j 向量存储还支持通过结合并行运行时和精确最近邻搜索来进行元数据过滤。需要 Neo4j 5.18 或更高版本。

相等性过滤具有以下语法。

existing_graph.similarity_search(
    "Slovenia",
    filter={"hobby": "Bicycle", "name": "Tomaz"},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

元数据过滤还支持以下运算符

$eq：等于
$ne：不等于
$lt：小于
$lte：小于或等于
$gt：大于
$gte：大于或等于
$in：在值列表中
$nin：不在值列表中
$between：在两个值之间
$like：文本包含值
$ilike：小写文本包含值

existing_graph.similarity_search(
    "Slovenia",
    filter={"hobby": {"$eq": "Bicycle"}, "age": {"$gt": 15}},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

您还可以使用过滤器之间的OR运算符

existing_graph.similarity_search(
    "Slovenia",
    filter={"$or": [{"hobby": {"$eq": "Bicycle"}}, {"age": {"$gt": 15}}]},
)

[Document(page_content='\nname: Tomaz\nlocation: Slovenia', metadata={'age': 33, 'hobby': 'Bicycle'})]

添加文档

我们可以将文档添加到现有的向量存储中。

store.add_documents([Document(page_content="foo")])

['acbd18db4cc2f85cedef654fccc4a4d8']

docs_with_score = store.similarity_search_with_score("foo")

docs_with_score[0]

(Document(page_content='foo'), 0.9999997615814209)

使用检索查询自定义响应

您还可以通过使用自定义 Cypher 代码段来获取图形中的其他信息来自定义响应。在幕后，最终的 Cypher 语句的构造方式如下

read_query = (
  "CALL db.index.vector.queryNodes($index, $k, $embedding) "
  "YIELD node, score "
) + retrieval_query

检索查询必须返回以下三列

text：Union[str, Dict] = 用于填充文档的page_content的值
score：Float = 相似度得分
metadata：Dict = 文档的其他元数据

在此博文中了解更多信息。

retrieval_query = """
RETURN "Name:" + node.name AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1)

[Document(page_content='Name:Tomaz', metadata={'foo': 'bar'})]

以下是如何将所有节点属性（embedding除外）作为字典传递到text列的示例，

retrieval_query = """
RETURN node {.name, .age, .hobby} AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1)

[Document(page_content='name: Tomaz\nage: 33\nhobby: Bicycle\n', metadata={'foo': 'bar'})]

您还可以将 Cypher 参数传递到检索查询。参数可用于其他过滤、遍历等…

retrieval_query = """
RETURN node {.*, embedding:Null, extra: $extra} AS text, score, {foo:"bar"} AS metadata
"""
retrieval_example = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name="person_index",
    retrieval_query=retrieval_query,
)
retrieval_example.similarity_search("Foo", k=1, params={"extra": "ParamInfo"})

[Document(page_content='location: Slovenia\nextra: ParamInfo\nname: Tomaz\nage: 33\nhobby: Bicycle\nembedding: None\n', metadata={'foo': 'bar'})]

混合搜索（向量 + 关键字）

Neo4j 集成了向量和关键字索引，这使您可以使用混合搜索方法

# The Neo4jVector Module will connect to Neo4j and create a vector and keyword indices if needed.
hybrid_db = Neo4jVector.from_documents(
    docs,
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    search_type="hybrid",
)

要从现有索引加载混合搜索，您必须同时提供向量和关键字索引

index_name = "vector"  # default index name
keyword_index_name = "keyword"  # default keyword index name

store = Neo4jVector.from_existing_index(
    OpenAIEmbeddings(),
    url=url,
    username=username,
    password=password,
    index_name=index_name,
    keyword_index_name=keyword_index_name,
    search_type="hybrid",
)

检索器选项

本节介绍如何将Neo4jVector用作检索器。

retriever = store.as_retriever()
retriever.invoke(query)[0]

Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': '../../how_to/state_of_the_union.txt'})

带来源的问答

本节介绍如何对索引上的来源进行问答。它通过使用RetrievalQAWithSourcesChain来实现，该链从索引中查找文档。

from langchain.chains import RetrievalQAWithSourcesChain
from langchain_openai import ChatOpenAI

API 参考：RetrievalQAWithSourcesChain | ChatOpenAI

chain = RetrievalQAWithSourcesChain.from_chain_type(
    ChatOpenAI(temperature=0), chain_type="stuff", retriever=retriever
)

chain.invoke(
    {"question": "What did the president say about Justice Breyer"},
    return_only_outputs=True,
)

{'answer': 'The president honored Justice Stephen Breyer for his service to the country and mentioned his retirement from the United States Supreme Court.\n',
 'sources': '../../how_to/state_of_the_union.txt'}

向量存储概念指南
向量存储操作指南

Neo4j 向量索引

使用余弦距离的相似性搜索（默认）

使用向量存储

元数据过滤

添加文档

使用检索查询自定义响应

混合搜索（向量 + 关键字）

检索器选项

带来源的问答

此页面是否有帮助？

您还可以留下详细的反馈在 GitHub 上.

使用余弦距离的相似性搜索（默认）​

使用向量存储​

元数据过滤​

添加文档​

使用检索查询自定义响应​

混合搜索（向量 + 关键字）​

检索器选项​

带来源的问答​

相关​

此页面是否有帮助？

您还可以留下详细的反馈 在 GitHub 上.

使用余弦距离的相似性搜索（默认）

使用向量存储

元数据过滤

添加文档

使用检索查询自定义响应

混合搜索（向量 + 关键字）

检索器选项

带来源的问答

相关

您还可以留下详细的反馈在 GitHub 上.