> 使用 postgres 作为后端并利用 pgvector extension.

代码位于名为 langchain-postgres.

状态

此代码已从 langchain-community 移植到名为 langchain-postgres的专用包中。以下更改已生效：

• * langchain-postgres 仅适用于 psycopg3。请将您的连接字符串从 postgresql+psycopg2://... to postgresql+psycopg://langchain:langchain@... （是的，驱动名称是 psycopg 不是 psycopg3，但它将使用 psycopg3.
• * 嵌入存储和集合的架构已更改，以使添加_文档能够正确处理用户指定的 ID。
• * 现在必须传递一个显式连接对象。

目前， **没有机制** 支持在架构更改时轻松迁移数据。向量存储中的任何架构更改都需要用户重新创建表并重新添加文档。 如果这是问题所在，请使用其他向量存储。如果不是，此实现应该适合您的用例。

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带有 pgvector extension:

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

凭据

运行此笔记本不需要凭据，只需确保您已下载 langchain-postgres 包并正确启动了 postgres 容器。

如果您想获得最佳的一流模型调用自动追踪，您还可以设置您的 LangSmith 通过取消注释以下内容来设置 API 密钥：

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

实例化

# | output: false
# | echo: false
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

向向量存储添加项目

请注意，通过 ID 添加文档将覆盖与该 ID 匹配的任何现有文档。

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])

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

从向量存储删除项目

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

查询向量存储

一旦您的向量存储创建完成并添加了相关文档，您很可能希望在链或代理运行期间对其进行查询。

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。

直接查询

执行简单的相似性搜索可以按如下方式进行：

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'}]

如果您提供包含多个字段但没有运算符的字典，顶层将被解释为逻辑 **AND** 过滤器

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')]

如果您想执行相似性搜索并接收相应的分数，您可以运行：

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'}]

有关可以在 PGVector 向量存储上执行的不同搜索的完整列表，请参阅 API 参考。

通过转换为检索器进行查询

您还可以将向量存储转换为检索器，以便在链中更方便地使用。

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')]

检索增强生成的使用方法

有关如何使用此向量存储进行检索增强生成 (RAG) 的指南，请参阅以下章节：

• - 检索文档
• - 使用 LangChain 构建 RAG 应用
• - 代理式 RAG

API 参考

有关所有 PGVector VectorStore 功能和配置的详细文档，请参阅 API 参考.