AI小道消息 · 10月5日 08:06

中文译文

又一个 Jev 的疯狂用例！传统的数据库过滤需要精确的、预先定义好的条件。但很多问题是语义性的：- 这篇文章主要讲的是软件工程吗？- 哪个主题最能描述它？- 它看起来技术深度如何？这些通常需要把行数据搬到应用代码中，调用一个模型，解析它的输出，然后再把结果写回。pg-jev 是一个开源的 Postgres 扩展，它通过 SQL 函数来暴露 Jev。- jev() 可以在 WHERE 中使用- jev_prob() 返回一个概率- jev_choice() 选出一个标签- jev_score() 在有序的层级上对行进行排名。它不需要向量列，也不需要 embedding 索引。在底层，pg-jev 会把行数据分批处理，发送给 Jev，然后返回类型化的答案，SQL 可以对这些答案进行过滤、排序、分组，并与精确的谓词组合使用。下面的录屏演示了它在存储于 Postgres 中的真实 Hacker News 故事上的运行效果。它首先展示了这些行，然后要求 Jev 找出软件工程相关的故事、按主题对它们分类，并按技术深度对它们进行排名。最后的查询会从数据库会话中报告请求次数、token 数、费用和缓存命中情况。GitHub 仓库：https://github.com/realZachi/pg-jev（别忘了给它点个 star ⭐）Postgres 负责保存数据并控制查询，而 Jev 负责处理 SQL 无法表示为确定性条件的那部分。如果你想了解 Jev 在底层到底在做什么，我还写了一篇动手指南，教你如何完全在本地用开源模型构建一个 Jev 风格的模型。请在下方阅读。

原文

Another insane Jev use case!Traditional database filters need precise, predefined conditions. But many questions are semantic:- Is this article mainly about software engineering?- Which topic best describes it?- How technically deep does it appear?These usually require moving rows into application code, invoking a model, parsing its output, and writing the result back.pg-jev is an open-source Postgres extension that exposes Jev through SQL functions.- jev() works inside WHERE- jev_prob() returns a probability- jev_choice() selects a label- jev_score() ranks rows across ordered levels.It needs no vector column or embedding index.Under the hood, pg-jev batches rows, sends them to Jev, and returns typed answers that SQL can filter, sort, group, and combine with exact predicates.The recording below runs it against real Hacker News stories stored in Postgres.It first shows the rows, then asks Jev to find software-engineering stories, classify them by topic, and rank them by technical depth. The final query reports requests, tokens, cost, and cache hits from the database session.GitHub repo: https://github.com/realZachi/pg-jev(don't forget to star it ⭐)Postgres keeps the data and controls the query, while Jev handles the part SQL cannot express as a deterministic condition.If you want to understand what Jev is doing under the hood, I also wrote a hands-on guide to building a Jev-style model with open models, entirely locally.Read it below.