PGVector

使用postgres作为后端并利用pgvector扩展实现的LangChain向量存储抽象。

代码位于一个名为：langchain_postgres 的集成包中。

状态​

该代码已从 langchain_community 迁移至一个名为 langchain-postgres 的独立软件包中。以下是所做的更改：

• langchain_postgres 仅支持 psycopg3。请将您的连接字符串从 postgresql+psycopg2://... 更新为 postgresql+psycopg://langchain:langchain@...（是的，驱动名称是 psycopg 而不是 psycopg3，但它会使用 psycopg3。
• 嵌入存储和集合的模式已更改，以使 add_documents 能够正确处理用户指定的 id。
• 现在必须传递一个显式的连接对象。

目前没有机制支持在模式更改时轻松迁移数据。因此，向量存储中的任何模式更改都将要求用户重新创建表并重新添加文档。 如果这是一个问题，请使用其他向量存储。如果不存在此问题，则此实现在您的使用场景中应该没有问题。

设置

首先下载合作伙伴包：

pip install -qU langchain_postgres

您可以运行以下命令来启动一个带有 pgvector 扩展的 postgres 容器：

%docker run --name pgvector-container -e POSTGRES_USER=langchain -e POSTGRES_PASSWORD=langchain -e POSTGRES_DB=langchain -p 6024:5432 -d pgvector/pgvector:pg16

Credentials

运行此笔记本无需任何凭据，只需确保您已下载 langchain_postgres 包并正确启动了 postgres 容器。

如果您想要获得最佳的模型调用自动化跟踪，您也可以通过取消注释下方代码来设置您的LangSmith API密钥。

# os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

Instantiation

选择 嵌入模型：

OpenAI

Azure

Google

AWS

HuggingFace

Ollama

Cohere

Mistral AI

Nomic

英伟达

Voyage AI

IBM watsonx

假

pip install -qU langchain-openai

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

from langchain_postgres import PGVector

# See docker command above to launch a postgres instance with pgvector enabled.
connection = "postgresql+psycopg://langchain:langchain@localhost:6024/langchain"  # Uses psycopg3!
collection_name = "my_docs"

vector_store = PGVector(
    embeddings=embeddings,
    collection_name=collection_name,
    connection=connection,
    use_jsonb=True,
)

管理向量存储

添加项到向量存储

请注意，通过ID添加文档将覆盖任何具有相同ID的现有文档。

from langchain_core.documents import Document

docs = [
    Document(
        page_content="there are cats in the pond",
        metadata={"id": 1, "location": "pond", "topic": "animals"},
    ),
    Document(
        page_content="ducks are also found in the pond",
        metadata={"id": 2, "location": "pond", "topic": "animals"},
    ),
    Document(
        page_content="fresh apples are available at the market",
        metadata={"id": 3, "location": "market", "topic": "food"},
    ),
    Document(
        page_content="the market also sells fresh oranges",
        metadata={"id": 4, "location": "market", "topic": "food"},
    ),
    Document(
        page_content="the new art exhibit is fascinating",
        metadata={"id": 5, "location": "museum", "topic": "art"},
    ),
    Document(
        page_content="a sculpture exhibit is also at the museum",
        metadata={"id": 6, "location": "museum", "topic": "art"},
    ),
    Document(
        page_content="a new coffee shop opened on Main Street",
        metadata={"id": 7, "location": "Main Street", "topic": "food"},
    ),
    Document(
        page_content="the book club meets at the library",
        metadata={"id": 8, "location": "library", "topic": "reading"},
    ),
    Document(
        page_content="the library hosts a weekly story time for kids",
        metadata={"id": 9, "location": "library", "topic": "reading"},
    ),
    Document(
        page_content="a cooking class for beginners is offered at the community center",
        metadata={"id": 10, "location": "community center", "topic": "classes"},
    ),
]

vector_store.add_documents(docs, ids=[doc.metadata["id"] for doc in docs])

API 参考:文档

[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

删除向量存储中的项

vector_store.delete(ids=["3"])

查询向量存储

一旦您的向量存储已经创建并添加了相关文档，您很可能在运行链或代理的过程中希望对其进行查询。

过滤支持​

向量存储支持一组可应用于文档元数据字段的过滤器。

操作员	含义/类别
$eq	Equality (==)
$ne	Inequality (!=)
$lt	Less than (<)
$lte	Less than or equal (<=)
$gt	Greater than (>)
$gte	Greater than or equal (>=)
$in	Special Cased (in)
$nin	Special Cased (not in)
$between	Special Cased (between)
$like	Text (like)
$ilike	Text (case-insensitive like)
$and	Logical (and)
$or	Logical (or)

查询直接

简单进行相似性搜索可以按照以下方式进行：

results = vector_store.similarity_search(
    "kitty", k=10, filter={"id": {"$in": [1, 5, 2, 9]}}
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

* there are cats in the pond [{'id': 1, 'topic': 'animals', 'location': 'pond'}]
* the library hosts a weekly story time for kids [{'id': 9, 'topic': 'reading', 'location': 'library'}]
* ducks are also found in the pond [{'id': 2, 'topic': 'animals', 'location': 'pond'}]
* the new art exhibit is fascinating [{'id': 5, 'topic': 'art', 'location': 'museum'}]

如果提供一个包含多个字段的字典但没有提供操作符，则顶层将被解释为逻辑 与 筛选

vector_store.similarity_search(
    "ducks",
    k=10,
    filter={"id": {"$in": [1, 5, 2, 9]}, "location": {"$in": ["pond", "market"]}},
)

[Document(metadata={'id': 1, 'topic': 'animals', 'location': 'pond'}, page_content='there are cats in the pond'),
 Document(metadata={'id': 2, 'topic': 'animals', 'location': 'pond'}, page_content='ducks are also found in the pond')]

vector_store.similarity_search(
    "ducks",
    k=10,
    filter={
        "$and": [
            {"id": {"$in": [1, 5, 2, 9]}},
            {"location": {"$in": ["pond", "market"]}},
        ]
    },
)

[Document(metadata={'id': 1, 'topic': 'animals', 'location': 'pond'}, page_content='there are cats in the pond'),
 Document(metadata={'id': 2, 'topic': 'animals', 'location': 'pond'}, page_content='ducks are also found in the pond')]

如果您想要执行相似性搜索并接收相应的评分，可以运行：

results = vector_store.similarity_search_with_score(query="cats", k=1)
for doc, score in results:
    print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")

* [SIM=0.763449] there are cats in the pond [{'id': 1, 'topic': 'animals', 'location': 'pond'}]

对于可以在PGVector向量存储上执行的各种搜索的完整列表，请参考API 参考文档。

查询通过转换为检索器

您也可以将向量存储转换为检索器，以便在链条中更方便地使用。

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 1})
retriever.invoke("kitty")

[Document(metadata={'id': 1, 'topic': 'animals', 'location': 'pond'}, page_content='there are cats in the pond')]

使用检索增强生成

对于如何使用此向量存储进行检索增强生成（RAG）的指南，请参见以下部分：

• 教程
• 如何使用RAG进行问答
• 检索概念文档

API 参考

有关所有 __ModuleName__VectorStore 功能和配置的详细文档，请访问 API 参考： https://python.langchain.com/api_reference/postgres/vectorstores/langchain_postgres.vectorstores.PGVector.html

相关

• 向量存储 概念指南
• 向量存储 使用指南