Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Cloudflare Clairic targets fast, low-cost data extraction

AI summary

The supplied report describes Clairic as Cloudflare’s AI model for fast, inexpensive data extraction. It provides no technical specifications, benchmark results, pricing, or details distinguishing Clairic from other data-extraction models.

In-depth insight

Clairic’s stated focus is fast, low-cost data extraction, but the available report does not provide enough evidence to assess its performance or broader significance.

10月28日消息,北京时间 10 月 19 日,Cloudflare 正式在 Workers AI 平台上线全新抽取模型 Clairic 预览版,该模型属于 System One 全新品类抽取模型,区别于传统大模型逐 token 生成文本,直接输出带数据类型的结构化结果,Cloudflare 表示后续计划开放模型权重。

Clairic 和 Cloudflare 此前推出的 Clef 决策模型形成互补:Clef 适合在预先给定的选项中做选择;而 Clairic 面向无法提前枚举答案的业务场景,例如解析发票总金额、提取交货日期、计算物流延误天数、预估维修费用等。

开发者传入原始文本内容(state)与自定义字段 Schema,模型可以从原文提取、现场运算,甚至做预测推演,返回每个字段对应的强类型数值;信息不足无法判定时直接返回 null ,不会编造结果,同时支持最多 4 张图片作为输入材料。

模型采用单次前向推理处理输入,支持 7 大类数据类型。估算、预测类结果输出中位数与 80% 置信区间,还可开启获取 99 分位数全套数据。

#Cloudflare#Clairic

Original · 2 min readRead the original
Group chat

No comments yet. Start the conversation.