upstash/vector
Composer 安装命令:
composer require upstash/vector
包简介
An HTTP/REST based Vector DB client built on top of Upstash REST API.
README 文档
README
Upstash Vector is an HTTP serverless Vector Database.
You can store, query, and retrieve vectors from your application, use it to power your search, and more.
You can read more about Upstash Vector here.
Quick Start
Installation
You can install the package via composer:
composer require upstash/vector
Create Index
Create a new index on Upstash
Usage
Initialize the index
use Upstash\Vector\Index; // Initialize the index $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); // or just to use the environment variables $index = Index::fromEnv();
Upserting Vectors
use Upstash\Vector\Index; use Upstash\Vector\VectorUpsert; use function Upstash\Vector\createRandomVector; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->upsert(new VectorUpsert( id: 'upstash-rocks', vector: createRandomVector(dimensions: 1536), metadata: ['field' => 'value'], ));
Upserting Data with Embedding Models
use Upstash\Vector\Index; use Upstash\Vector\DataUpsert; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->upsertData(new DataUpsert( id: 'upstash-vector', data: 'Upstash Vector is a serverless vector database.', metadata: ['field' => 'value'], ));
Querying Vectors
use Upstash\Vector\Index; use Upstash\Vector\VectorQuery; use function Upstash\Vector\createRandomVector; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->query(new VectorQuery( vector: createRandomVector(dimensions: 1536), topK: 5, ));
Querying Data with Embedding Models
use Upstash\Vector\Index; use Upstash\Vector\DataQuery; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->queryData(new DataQuery( data: 'What is Upstash Vector?', topK: 5, ));
Fetch specific vectors
use Upstash\Vector\Index; use Upstash\Vector\VectorFetch; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->fetch(new VectorFetch(ids: ['upstash-rocks']));
Delete specific vectors
use Upstash\Vector\Index; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); $index->delete(['upstash-rocks']);
Namespaces
Upstash Vector allows you to partition a single index into multiple isolated namespaces. Each namespace functions as a self-contained subset of the index, in which read and write requests are only limited to one namespace. To learn more about it, see Namespaces.
Example
use Upstash\Vector\Index; use Upstash\Vector\VectorUpsert; use function Upstash\Vector\createRandomVector; $index = new Index( url: 'UPSTASH_VECTOR_REST_URL', token: 'UPSTASH_VECTOR_REST_TOKEN', ); // Upsert to namespace $index->namespace('books')->upsert(new VectorUpsert( id: 'upstash-rocks', vector: createRandomVector(dimensions: 1536), metadata: ['field' => 'value'], ));
Troubleshooting
We have a Discord for common problems. If you can't find a solution, please open an issue.
Testing
composer test
Changelog
Please see CHANGELOG for more information on what has changed recently.
upstash/vector 适用场景与选型建议
upstash/vector 是一款 基于 PHP 开发的 Composer 扩展包,目前已累计 9.96k 次下载、GitHub Stars 达 5, 最近一次更新时间为 2025 年 01 月 15 日, 在 PHP 生态内属于活跃度较高的组件。
它主要适用于以下技术方向: 「php」 「sdk」 「vector」 「ai」 「rag」 「upstash」 等业务场景。在实际项目中,围绕这些方向常见需要落地的问题包括:接口对接、性能调优、并发安全、与既有框架(Laravel / ThinkPHP / Yii / Webman 等)的兼容适配,以及生产环境的日志埋点与稳定性保障。
我们在过去多个企业项目中使用过 upstash/vector 或与其功能相近的方案,如果你在选型或落地过程中遇到问题,例如 版本兼容、二次改造、私有化封装、与内部系统对接、生产 BUG 排查,欢迎联系我们协助评估。
基于 upstash/vector 在你已有业务上做功能扩展、字段裁剪、UI 适配、与内部账号 / 权限 / 日志系统的深度对接。
线上偶发问题、内存泄漏、慢查询、并发异常等排查修复;针对高流量场景做缓存、队列、索引层面的调优。
承接完整的项目从需求 → 设计 → 开发 → 上线 → 长期运维;也可按月提供技术保姆服务。
与 upstash/vector 相关的其它包
同方向 / 同关键字的高下载量 PHP Composer 包推荐,方便对比选型:
Generic, object-oriented Vector, Map, and Set collections with immutable and mutable variants
Immutable data structures based on php/ds.
Simple PHP client for Qdrant vector database. Easy-to-use library for storing, searching, and managing vector embeddings in AI and machine learning applications.
A modern Laravel package for SVG conversion with multiple provider support (Resvg, Inkscape, rsvg-convert). Convert SVG to PNG, PDF, EPS, and more.
Laravel semantic search package with static code analysis and context-aware query building.
Math lib for php 7.1+.
统计信息
- 总下载量: 9.96k
- 月度下载量: 0
- 日度下载量: 0
- 收藏数: 5
- 点击次数: 17
- 依赖项目数: 1
- 推荐数: 0
其他信息
- 授权协议: MIT
- 更新时间: 2025-01-15