FireCrawl 用新自定义模型提取相关上下文

Under the hood, we now use a new custom model to pull the most relevant context from each result. I...

精选理由

FireCrawl 出了新模型,自动对网页段落打分,只给你最相关的摘要,省 token 还好用。

AI 摘要

FireCrawl 更新了其底层模型,使用新的自定义模型对每个段落、列表和表格进行相关性评分。该模型能够根据用户查询自动提取最相关的关键摘录,减少智能体在处理噪声页面时的 token 浪费。官方表示此举旨在提升检索结果的精确性和 token 利用效率。

图片来源 · Firecrawl
原文 · Firecrawl

Under the hood, we now use a new custom model to pull the most relevant context from each result. I...

Under the hood, we now use a new custom model to pull the most relevant context from each result. It scores every paragraph, list, and table against your query, so agents get key excerpts without having to waste tokens processing noisy pages. Your browser does not support the video tag. 🔗 View on Twitter 💬 1 🔄 0 ❤️ 8 👀 404 📊 2 ⚡