使用 SQLiteVec 将 SQLite 作为矢量存储

使用 SQLiteVec 将 SQLite 作为矢量存储

本笔记本介绍了如何开始使用 SQLite-Vec 向量存储。

SQLite-Vec 是一个为向量搜索设计的 SQLite 扩展，强调本地优先操作，并且易于集成到无需外部服务器的应用程序中。它是同一作者创建的 SQLite-VSS 的后继者。它是用零依赖 C 语言编写的，设计目的是易于构建和使用。

本笔记本演示了如何使用 SQLiteVec 矢量数据库。

设置

您需要使用 pip install -qU langchain-community 安装 langchain-community 才能使用这个集成。

# You need to install sqlite-vec as a dependency.
%pip install --upgrade --quiet  sqlite-vec

凭据

SQLiteVec 不需要任何凭据即可使用，因为 vector store 是一个简单的 SQLite 文件。

初始化

from langchain_community.embeddings.sentence_transformer import (
    SentenceTransformerEmbeddings,
)
from langchain_community.vectorstores import SQLiteVec

embedding_function = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
vector_store = SQLiteVec(
    table="state_union", db_file="/tmp/vec.db", embedding=embedding_function
)

管理 vector store

将项目添加到 vector store

vector_store.add_texts(texts=["Ketanji Brown Jackson is awesome", "foo", "bar"])

更新 vector store 中的项目

尚不支持

从向量存储中删除项目

尚不支持

查询向量存储

直接查询

data = vector_store.similarity_search("Ketanji Brown Jackson", k=4)

通过转换为检索器进行查询

尚不支持

用于检索增强型生成

有关如何使用它进行检索增强型生成的更多信息，请参阅 https://alexgarcia.xyz/sqlite-vec/ 上的 sqlite-vec 文档。

API 参考

有关所有 SQLiteVec 功能和配置的详细文档，请访问 API 参考：https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.sqlitevec.SQLiteVec.html

其他示例

from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings.sentence_transformer import (
    SentenceTransformerEmbeddings,
)
from langchain_community.vectorstores import SQLiteVec
from langchain_text_splitters import CharacterTextSplitter

# load the document and split it into chunks
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()

# split it into chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
texts = [doc.page_content for doc in docs]


# create the open-source embedding function
embedding_function = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")


# load it in sqlite-vss in a table named state_union.
# the db_file parameter is the name of the file you want
# as your sqlite database.
db = SQLiteVec.from_texts(
    texts=texts,
    embedding=embedding_function,
    table="state_union",
    db_file="/tmp/vec.db",
)

# query it
query = "What did the president say about Ketanji Brown Jackson"
data = db.similarity_search(query)

# print results
data[0].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.’

使用现有 SQLite 连接的示例

from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings.sentence_transformer import (
    SentenceTransformerEmbeddings,
)
from langchain_community.vectorstores import SQLiteVec
from langchain_text_splitters import CharacterTextSplitter

# load the document and split it into chunks
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()

# split it into chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
texts = [doc.page_content for doc in docs]


# create the open-source embedding function
embedding_function = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
connection = SQLiteVec.create_connection(db_file="/tmp/vec.db")

db1 = SQLiteVec(
    table="state_union", embedding=embedding_function, connection=connection
)

db1.add_texts(["Ketanji Brown Jackson is awesome"])
# query it again
query = "What did the president say about Ketanji Brown Jackson"
data = db1.similarity_search(query)

# print results
data[0].page_content

‘Ketanji Brown Jackson is awesome’