跳到主要内容

PGVector

一个使用 postgres 作为后端并利用 pgvector 扩展的 LangChain 向量存储抽象的实现。

该代码位于名为 langchain_postgres 的集成包中。

状态

此代码已从 langchain_community 移植到一个名为 langchain-postgres 的专用包中。已进行以下更改

  • langchain_postgres 仅适用于 psycopg3。请将您的连接字符串从 postgresql+psycopg2://... 更新为 postgresql+psycopg://langchain:langchain@... (是的,驱动程序名称是 psycopg 而不是 psycopg3,但它会使用 psycopg3。)
  • 嵌入存储和集合的架构已更改,以便使 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,没有机制支持在架构更改时轻松迁移数据。因此,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。如果这是一个问题,请使用不同的向量存储。如果不是,则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

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。

如果您想获得一流的模型调用自动跟踪,您还可以通过取消注释下方来设置您的 LangSmith API 密钥

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

实例化

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_core.documents import Document
from langchain_postgres import PGVector
from langchain_postgres.vectorstores 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,
)
API 参考:文档

管理向量存储

向向量存储添加项

请注意,按 ID 添加文档将覆盖任何与该 ID 匹配的现有文档。

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

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

查询向量存储

一旦您的向量存储已创建并添加了相关文档,您很可能希望在链或代理的运行期间查询它。

筛选支持

向量存储支持一组可以针对文档的元数据字段应用的筛选器。

运算符含义/类别
$eq相等 (==)
$ne不相等 (!=)
$lt小于 (<)
$lte小于或等于 (<=)
$gt大于 (>)
$gte大于或等于 (>=)
$in特殊情况 (in)
$nin特殊情况 (not in)
$between特殊情况 (between)
$like文本 (like)
$ilike文本 (不区分大小写的 like)
$and逻辑 (and)
$or逻辑 (or)

直接查询

可以按如下方式执行简单的相似性搜索

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'}]

如果您提供一个包含多个字段但没有运算符的 dict,则顶层将被解释为逻辑 AND 筛选器

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

通过转换为检索器查询

您还可以将向量存储转换为检索器,以便在您的链中更轻松地使用。

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')]

用于检索增强生成的用法

有关如何将此向量存储用于检索增强生成 (RAG) 的指南,请参阅以下部分

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.ac.cn/api_reference/postgres/vectorstores/langchain_postgres.vectorstores.PGVector.html


此页内容是否对您有帮助?