向量数据库学习笔记(2) —— pgvector 简介与用法

关于向量的基础概念,可以参考:向量数据库学习笔记(1) —— 基础概念-优快云博客

一、 pgvector简介

       pgvector 是一款开源的、基于pg的、向量相似性搜索 插件,将您的向量数据与其他数据统一存储在pg中。支持功能包括:

  • 精确与近似最近邻搜索
  • 单精度/半精度浮点向量、二进制向量及稀疏向量
  • 多种距离度量:L2距离、内积、余弦距离、L1距离、汉明距离、杰卡德距离
  • 支持所有具有Postgres客户端的编程语言
  • 同时继承PostgreSQL全部核心优势

二、 安装与启用

https://github.com/pgvector/pgvector

下载并解压安装包

cd pgvector
make
make install

插件安装(注意它叫vector,不叫pgvector)

CREATE EXTENSION vector;

三、 简单用法

1. 建表与增删改

Create a new table with a vector column

CREATE TABLE items (id bigserial PRIMARY KEY, embedding vector(3));

add a vector column to an existing table

ALTER TABLE items ADD COLUMN embedding vector(3);

Insert vectors

INSERT INTO items (embedding) VALUES ('[1,2,3]'), ('[4,5,6]');

load vectors in bulk using COPY

COPY items (embedding) FROM STDIN WITH (FORMAT BINARY);

Upsert vectors

INSERT INTO items (id, embedding) VALUES (1, '[1,2,3]'), (2, '[4,5,6]')
    ON CONFLICT (id) DO UPDATE SET embedding = EXCLUDED.embedding;

Update vectors

UPDATE items SET embedding = '[1,2,3]' WHERE id = 1;

Delete vectors

DELETE FROM items WHERE id = 1;

2. 向量查询

Get the nearest neighbors to a vector

SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;

Supported distance functions are:

  • <-> - L2 distance
  • <#> - (negative) inner product
  • <=> - cosine distance
  • <+> - L1 distance
  • <~> - Hamming distance (binary vectors)
  • <%> - Jaccard distance (binary vectors)

Get the nearest neighbors to a row

SELECT * FROM items WHERE id != 1 ORDER BY embedding <-> (SELECT embedding FROM items WHERE id = 1) LIMIT 5;

Get rows within a certain distance

SELECT * FROM items WHERE embedding <-> '[3,1,2]' < 5;

Note: Combine with ORDER BY and LIMIT to use an index

3. 距离查询

Get the distance

SELECT embedding <-> '[3,1,2]' AS distance FROM items;

For inner product, multiply by -1 (since <#> returns the negative inner product)

SELECT (embedding <#> '[3,1,2]') * -1 AS inner_product FROM items;

For cosine similarity, use 1 - cosine distance

SELECT 1 - (embedding <=> '[3,1,2]') AS cosine_similarity FROM items;

4. 聚合查询

Average vectors

SELECT AVG(embedding) FROM items;

Average groups of vectors

SELECT category_id, AVG(embedding) FROM items GROUP BY category_id;

四、核心索引

pgvector支持两类索引,即前面提到过的两类算法 —— HNSW(默认) 与 IVFFlat。

1. HNSW索引

       HNSW索引会构建一个多层图结构。相比IVFFlat索引,它具有更优的查询性能(在搜索速度与召回率的权衡方面),但构建时间更长且内存占用更高。此外,由于不需要像IVFFlat那样的训练步骤,该索引可以在表内尚无数据时直接创建。

创建各类距离索引

L2 distance

CREATE INDEX ON items USING hnsw (embedding vector_l2_ops);

Note: Use halfvec_l2_ops for halfvec and sparsevec_l2_ops for sparsevec (and similar with the other distance functions)

Inner product

CREATE INDEX ON items USING hnsw (embedding vector_ip_ops);

Cosine distance

CREATE INDEX ON items USING hnsw (embedding vector_cosine_ops);

L1 distance

CREATE INDEX ON items USING hnsw (embedding vector_l1_ops);

Hamming distance

CREATE INDEX ON items USING hnsw (embedding bit_hamming_ops);

Jaccard distance

CREATE INDEX ON items USING hnsw (embedding bit_jaccard_ops);

Supported types are:

  • vector - up to 2,000 dimensions
  • halfvec - up to 4,000 dimensions
  • bit - up to 64,000 dimensions
  • sparsevec - up to 1,000 non-zero elements

2. IVFFlat索引

       IVFFlat索引的工作原理是将向量划分为多个聚类列表,仅搜索距离查询向量最近的若干列表。相较于HNSW索引,它具有更快的构建速度和更低的内存占用,但在查询性能(速度与召回率的平衡)方面表现稍逊。

       IVFFlat索引实现高召回率需把握三个关键要点:

  • 数据准备:建议在表中已存有数据后再创建索引

  • 列表数量设定:

    • 数据量≤100万条时,建议初始值为行数/1000

    • 数据量>100万条时,建议采用行数的平方根值

  • 查询调优:设置合适的探测数量(probes参数)

    • 较高值提升召回率,较低值加快查询速度

    • 建议初始值为列表数量的平方根值

创建各类距离索引

L2 distance

CREATE INDEX ON items USING ivfflat (embedding vector_l2_ops) WITH (lists = 100);

Note: Use halfvec_l2_ops for halfvec (and similar with the other distance functions)

Inner product

CREATE INDEX ON items USING ivfflat (embedding vector_ip_ops) WITH (lists = 100);

Cosine distance

CREATE INDEX ON items USING ivfflat (embedding vector_cosine_ops) WITH (lists = 100);

Hamming distance

CREATE INDEX ON items USING ivfflat (embedding bit_hamming_ops) WITH (lists = 100);

Supported types are:

  • vector - up to 2,000 dimensions
  • halfvec - up to 4,000 dimensions
  • bit - up to 64,000 dimensions

五、 其他向量及索引

半精度向量(Half-Precision Vectors)
  • 存储半精度向量:

    CREATE TABLE items (id bigserial PRIMARY KEY, embedding halfvec(3));
  • 半精度索引:

    CREATE INDEX ON items USING hnsw ((embedding::halfvec(3)) halfvec_l2_ops);
  • 最近邻查询:

    SELECT * FROM items ORDER BY embedding::halfvec(3) <-> '[1,2,3]' LIMIT 5;

二进制向量(Binary Vectors)
  • 存储二进制向量:

    CREATE TABLE items (id bigserial PRIMARY KEY, embedding bit(3));
    INSERT INTO items (embedding) VALUES ('000'), ('111');
  • 汉明距离查询:

    SELECT * FROM items ORDER BY embedding <~> '101' LIMIT 5;
  • Jaccard 距离支持:

    SELECT * FROM items ORDER BY embedding <%> '101' LIMIT 5;

稀疏向量(Sparse Vectors)
  • 存储稀疏向量(格式:{索引:值,...}/维度,索引从 1 开始):

    sql

    复制

    CREATE TABLE items (id bigserial PRIMARY KEY, embedding sparsevec(5));
    INSERT INTO items (embedding) VALUES ('{1:1,3:2,5:3}/5'), ('{1:4,3:5,5:6}/5');
  • L2 距离查询:

    SELECT * FROM items ORDER BY embedding <-> '{1:3,3:1,5:2}/5' LIMIT 5;

参考

部分内容来自AI回答

https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw

在 PostgreSQL 中为生成式 AI 应用程序查询向量数据的最佳实践_哔哩哔哩_bilibili

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

Hehuyi_In

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值