Products

You.com 推出 Extract API:读取网页与 PDF 内容

Why we picked it

You.com 出了个 Extract API,网页和 PDF 都能抓来解析,表格、扫描件都能转成结构化数据,官方说 PDF 准确率比之前高 80%,还能选零数据留存。做 Agent 或者要批量啃文档的开发者可以先去 playground 免费试试。

You.com 发布 Extract API,可抓取并解析任意网页或 PDF,官方称在 ParseBench-2 基准上 PDF 解析准确率提升 80%。

Body

它支持把表格、图表、表单和扫描件转换为结构化输出,网页试用在 playground 中无需 API key 即可开始。对包含敏感文档的场景,API 还提供 ZDR(零数据留存)选项。

这直指智能体工作流中一个常见瓶颈:大量世界信息以 PDF 形式存在,解析质量决定 Agent 能读到什么。

Original · Richard Socher

Agents are only as good as what they can read. A lot of the world’s info is stuck in PDFs: tables, charts, forms, and scans. The new @youdotcom Extract API can read it, with 80% higher PDF accuracy on ParseBench-2. Try it today in the playground. You.com @youdotcom Introducing Extract API. Fetch and parse any web page or PDF. 80% higher PDF accuracy on ParseBench-2. → Structured Tables, charts, forms, and scans → Try on web pages, no API key required to start → ZDR available for sensitive docs Try it at you.com/platform/playg…

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include You.com, Extract API, PDF parsing, agents.

Source attribution: curated from Richard Socher (@RichardSocher).