pg_pinecone 现可在 Railway 一键部署
该 Railway 模板运行的是 Postgres 18,并已安装、预加载并启用 pg_pinecone,因此无需安装扩展或构建镜像。在我们针对 100 万向量的基准测试中,使用 halfvec 时,pg_pinecone 索引比 pgvector HNSW 索引小约 15 倍,并在相同召回率下返回结果更快。Railway 按服务使用的内存和存储计费,因此更小的索引能让同一个 Postgres 服务在相同成本下容纳多得多的向量。当某张表需要扩展时,只需一个 Pinecone API 密钥和一次 SQL 调用,就能将其搜索迁移到 Pinecone 托管服务中的无服务器索引,再一次调用即可迁回。无论向量存储在何处,查询都无需改动。
pg_pinecone 模板现已在 Railway 的模板市场上架,pg_pinecone 扩展以 Apache 2.0 协议开源。其原生引擎是 pg_pinecone 的默认选项,在 Postgres 内部运行,无需 Pinecone 账户。
要开始使用,可在 Railway 上部署该模板,或阅读 pg_pinecone 快速入门。
这篇文章对你有帮助吗?
今天就着手构建具备知识能力的 AI
免费创建你的第一个索引,待准备扩展时再按用量付费。
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(pg_pinecone now deploys on Railway in one click)
The Railway template runs Postgres 18 with pg_pinecone installed, preloaded, and enabled, so there's no extension to install or image to build. In our benchmarks on 1 million vectors, the pg_pinecone index was about 15 times smaller than a pgvector HNSW index using halfvec and returned results faster at the same recall. Railway bills for the memory and storage a service uses, so a smaller index lets the same Postgres service hold many more vectors for the same cost. When a table needs to scale, a Pinecone API key and one SQL call move its search to a serverless index in Pinecone's managed service, and another call moves it back. Wherever the vectors are stored, queries don't change.
The pg_pinecone template is available now in Railway's template marketplace, and the pg_pinecone extension is open source under Apache 2.0. The native engine, pg_pinecone's default, runs inside Postgres and needs no Pinecone account.
To get started, deploy the template on Railway, or read the pg_pinecone quickstart.
Was this article helpful?
Start building knowledgeable AI today
Create your first index for free, then pay as you go when you're ready to scale.
原文为英文,正文由自动抓取并保留原文。
原文发布于 Pinecone Blog(pg_pinecone now deploys on Railway in one click),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。