Supabase (Postgres)

Supabase 是一个开源的 Firebase 替代品。 Supabase 建立在 PostgreSQL 之上，提供强大的 SQL 查询能力，并与现有工具和框架实现简单的接口。

PostgreSQL，也称为 Postgres，是一个免费的开源关系数据库管理系统 (RDBMS)，强调可扩展性和 SQL 兼容性。
Supabase 提供一个开源工具包，用于使用 Postgres 和 pgvector 开发 AI 应用程序。使用 Supabase 客户端库按规模存储、索引和查询您的向量嵌入。

在笔记本中，我们将演示围绕 Supabase 向量存储的 SelfQueryRetriever。

具体来说，我们将：

创建一个 Supabase 数据库
启用 pgvector 扩展
创建一个 documents 表和 match_documents 函数，供 SupabaseVectorStore 使用
将示例文档加载到向量存储（数据库表）中
构建并测试自查询检索器

设置 Supabase 数据库

前往 https://database.new 来配置你的 Supabase 数据库。

在控制台中，跳转到 SQL 编辑器，并运行以下脚本以启用 pgvector 并将你的数据库设置为向量存储：

-- Enable the pgvector extension to work with embedding vectors
create extension if not exists vector;

-- Create a table to store your documents
create table
  documents (
    id uuid primary key,
    content text, -- corresponds to Document.pageContent
    metadata jsonb, -- corresponds to Document.metadata
    embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed
  );

-- Create a function to search for documents
create function match_documents (
  query_embedding vector (1536),
  filter jsonb default '{}'
) returns table (
  id uuid,
  content text,
  metadata jsonb,
  similarity float
) language plpgsql as $$
#variable_conflict use_column
begin
  return query
  select
    id,
    content,
    metadata,
    1 - (documents.embedding <=> query_embedding) as similarity
  from documents
  where metadata @> filter
  order by documents.embedding <=> query_embedding;
end;
$$;

创建 Supabase 向量存储

接下来，我们将创建一个 Supabase 向量存储并用一些数据进行初始化。我们创建了一小组包含电影摘要的示例文档。

确保安装最新版本的 langchain 及其 openai 支持：

%pip install --upgrade --quiet  langchain langchain-openai tiktoken

自查询检索器需要您安装 lark：

%pip install --upgrade --quiet  lark

我们还需要 supabase 包：

%pip install --upgrade --quiet  supabase

由于我们使用 SupabaseVectorStore 和 OpenAIEmbeddings，我们必须加载它们的 API 密钥。

要找到您的 SUPABASE_URL 和 SUPABASE_SERVICE_KEY，请前往您的 Supabase 项目的 API 设置。
- SUPABASE_URL 对应于项目 URL
- SUPABASE_SERVICE_KEY 对应于 service_role API 密钥
要获取您的 OPENAI_API_KEY，请在您的 OpenAI 账户中导航到 API 密钥并创建一个新的密钥。

import getpass
import os

os.environ["SUPABASE_URL"] = getpass.getpass("Supabase URL:")
os.environ["SUPABASE_SERVICE_KEY"] = getpass.getpass("Supabase Service Key:")
os.environ["OPENAI_API_KEY"] = getpass.getpass("OpenAI API Key:")

可选： 如果您将 Supabase 和 OpenAI API 密钥存储在 .env 文件中，可以使用 dotenv 加载它们。

%pip install --upgrade --quiet  python-dotenv

from dotenv import load_dotenv

load_dotenv()

首先，我们将创建一个 Supabase 客户端并实例化一个 OpenAI 嵌入类。

import os

from langchain_community.vectorstores import SupabaseVectorStore
from langchain_core.documents import Document
from langchain_openai import OpenAIEmbeddings
from supabase.client import Client, create_client

supabase_url = os.environ.get("SUPABASE_URL")
supabase_key = os.environ.get("SUPABASE_SERVICE_KEY")
supabase: Client = create_client(supabase_url, supabase_key)

embeddings = OpenAIEmbeddings()

接下来，让我们创建我们的文档。

docs = [
    Document(
        page_content="A bunch of scientists bring back dinosaurs and mayhem breaks loose",
        metadata={"year": 1993, "rating": 7.7, "genre": "science fiction"},
    ),
    Document(
        page_content="Leo DiCaprio gets lost in a dream within a dream within a dream within a ...",
        metadata={"year": 2010, "director": "Christopher Nolan", "rating": 8.2},
    ),
    Document(
        page_content="A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea",
        metadata={"year": 2006, "director": "Satoshi Kon", "rating": 8.6},
    ),
    Document(
        page_content="A bunch of normal-sized women are supremely wholesome and some men pine after them",
        metadata={"year": 2019, "director": "Greta Gerwig", "rating": 8.3},
    ),
    Document(
        page_content="Toys come alive and have a blast doing so",
        metadata={"year": 1995, "genre": "animated"},
    ),
    Document(
        page_content="Three men walk into the Zone, three men walk out of the Zone",
        metadata={
            "year": 1979,
            "director": "Andrei Tarkovsky",
            "genre": "science fiction",
            "rating": 9.9,
        },
    ),
]

vectorstore = SupabaseVectorStore.from_documents(
    docs,
    embeddings,
    client=supabase,
    table_name="documents",
    query_name="match_documents",
)

创建自查询检索器

现在我们可以实例化我们的检索器。为此，我们需要提前提供一些关于我们的文档支持的元数据字段的信息以及文档内容的简短描述。

from langchain.chains.query_constructor.base import AttributeInfo
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain_openai import OpenAI

metadata_field_info = [
    AttributeInfo(
        name="genre",
        description="The genre of the movie",
        type="string or list[string]",
    ),
    AttributeInfo(
        name="year",
        description="The year the movie was released",
        type="integer",
    ),
    AttributeInfo(
        name="director",
        description="The name of the movie director",
        type="string",
    ),
    AttributeInfo(
        name="rating", description="A 1-10 rating for the movie", type="float"
    ),
]
document_content_description = "Brief summary of a movie"
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(
    llm, vectorstore, document_content_description, metadata_field_info, verbose=True
)

测试一下

现在我们可以尝试实际使用我们的检索器！

# This example only specifies a relevant query
retriever.invoke("What are some movies about dinosaurs")

query='dinosaur' filter=None limit=None

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),
 Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),
 Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]

# This example only specifies a filter
retriever.invoke("I want to watch a movie rated higher than 8.5")

query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),
 Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]

# This example specifies a query and a filter
retriever.invoke("Has Greta Gerwig directed any movies about women?")

query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None

[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'})]

# This example specifies a composite filter
retriever.invoke("What's a highly rated (above 8.5) science fiction film?")

query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None

[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'})]

# This example specifies a query and composite filter
retriever.invoke(
    "What's a movie after 1990 but before (or on) 2005 that's all about toys, and preferably is animated"
)

query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='year', value=2005), Comparison(comparator=<Comparator.LIKE: 'like'>, attribute='genre', value='animated')]) limit=None

[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]

过滤 k

我们还可以使用自查询检索器来指定 k：要获取的文档数量。

我们可以通过将 enable_limit=True 传递给构造函数来实现这一点。

retriever = SelfQueryRetriever.from_llm(
    llm,
    vectorstore,
    document_content_description,
    metadata_field_info,
    enable_limit=True,
    verbose=True,
)

# 这个示例仅指定了一个相关查询
retriever.invoke("what are two movies about dinosaurs")

query='dinosaur' filter=None limit=2

[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),
 Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]

Supabase (Postgres)

设置 Supabase 数据库

创建 Supabase 向量存储

创建自查询检索器

测试一下

过滤 k

此页面是否有帮助？

您还可以留下详细的反馈在 GitHub 上

Supabase (Postgres)

设置 Supabase 数据库​

创建 Supabase 向量存储​

创建自查询检索器​

测试一下​

过滤 k​

此页面是否有帮助？

您还可以留下详细的反馈 在 GitHub 上

设置 Supabase 数据库

创建 Supabase 向量存储

创建自查询检索器

测试一下

过滤 k

您还可以留下详细的反馈在 GitHub 上