返回资讯中心
外部精选
软件工程
#开发者实时流

Show HN: Don't Get Nerf'd by Document Processing

We built doc extraction that owns the Pareto curve for almost 2 orders of magnitude.Cost efficient structured outputs: - Near frontier quality structured extraction - Up to 99% cheaper - Up to 3x fasterWe've been using …

Hacker News 最新jonappleseed222026/10/20 · 27 天前2 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

We built doc extraction that owns the Pareto curve for almost 2 orders of magnitude.Cost efficient structured outputs:

  • Near frontier quality structured extraction
  • Up to 99% cheaper
  • Up to 3x fasterWe've been using it under the hood at Pacific. Today we're releasing it broadly as a research experiment.It also bundles in a bunch of nice features to make the structured outputs more useful. You get citations with optional hosted citation urls with highlights, calibrated confidence values, and the option for zero data retention.Time to build with structured outputs at scale! Comments URL: https://news.ycombinator.com/item?id=50161085 Points: 1

Comments: 0

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →