PGVector 集成

使用 LangChain Python 集成 PGVector 向量存储。

使用 postgres 作为后端并集成 pgvector 扩展实现的 LangChain 向量存储抽象层。

代码位于名为 langchain-postgres 的集成包中。

状态

该代码已从 langchain-community 迁移到专用包 langchain-postgres，主要修改如下：

• langchain-postgres 仅支持 psycopg3 驱动。请将连接字符串从 postgresql+psycopg2://... 更新为 postgresql+psycopg://langchain:langchain@...（注意驱动名称是 psycopg 而非 psycopg3，但系统将使用 psycopg3）
• 嵌入存储和集合的架构已调整以支持用户自定义 ID 的文档添加
• 需显式传递连接对象

当前 没有机制 支持数据迁移。向量存储的架构变更需要用户手动重建表并重新添加文档。若此问题影响使用，建议选择其他向量存储方案。若无此需求，本实现适用于常规场景。

安装

首先下载合作伙伴包：

pip install -qU langchain-postgres

可通过以下命令启动带 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

凭据

无需运行笔记本时配置凭据，确保已下载 langchain-postgres 包并正确启动 Postgres 容器。

若需获取模型调用自动化追踪功能，可设置 LangSmith API 密钥（取消注释下方代码）：

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

初始化

# | 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

添加项目到向量存储

注意：通过 ID 添加文档会覆盖同名现有文档。

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]

删除项目从向量存储

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

查询向量存储

在链或智能体运行时查询向量存储是常见需求。

过滤支持

向量存储支持文档元数据字段过滤，支持以下操作符：

运算符	含义/类别
$eq	等于 (==)
$ne	不等于 (!=)
$lt	小于 (<)
$lte	小于等于 (<=)
$gt	大于 (>)
$gte	大于等于 (>=)
$in	特殊处理 (in)
$nin	特殊处理 (not in)
$between	特殊处理 (between)
$like	文本 (like)
$ilike	文本 (不区分大小写 like)
$and	逻辑 (and)
$or	逻辑 (or)

直接查询

执行简单相似度搜索：

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'}]

若提供多字段字典但无运算符，顶层会被视为逻辑 AND 过滤

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')]

若需获取相似度得分，可执行：

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'}]

完整向量存储 PGVector 支持的搜索类型请参考 [API reference][PGVector]。

转换为检索器

可将向量存储转换为检索器以适配链式流程：

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')]

检索增强生成使用

RAG 使用指南详见以下章节：

• 检索文档
• 使用 LangChain 构建 RAG 应用
• 智能体式 RAG

---

API 参考

获取 PGVector 向量存储所有功能及配置的详细文档，请访问 API reference。

---

官方原文：src/oss/python/integrations/vectorstores/pgvector.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。