传统 RAG 解析网页、PDF,经常把表格、图表和页面布局给弄丢。
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
传统 RAG 解析网页、PDF,经常把表格、图表和页面布局给弄丢。 PixelRAG 换了个思路:不拆 HTML、不只读文本,直接把网页和 PDF 转成截图,再用视觉索引做 RAG。 几个亮点: 1️⃣ 页面视觉信息基本完整保留 2️⃣ 官方测试准确率最高提升 18.1% 3️⃣ AI Agent 的 Token 消耗最高可降 10 倍 4️⃣ 已预建 828 万个 Wikipedia 页面索引 5️⃣ 还有 Claude 插件,直接让 AI“看图” 免费 API 也能直接玩,适合需要理解复杂网页和文档的场景。 🔗 https://github.com/StarTrail-org/PixelRAG
Posted by lumxss (24.7k followers) 5 h ago · 10 likes · 1k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: pixelrag.
More dev work like this
- 💥什么鬼!本地开源 Jev 居然杀到了 0 输出 Token,自带三档模型直接落地结构化判断! — @NFT_Chen
- AI Agent System for Deep Learning Model Migration from TensorFlow to JAX! #BigData… — @gp_pulipaka
- Vectorizing the Math for LLM! #BigData #Analytics #DataScience #AI #MachineLearning #IoT… — @gp_pulipaka
- Hermes Wingtips #79: `agent[.]disabled_toolsets` — @witcheer
- Give your coding agent a box — not your whole machine. — @DanKornas
- it's awesome to see the reception here 🔥 — @jerryjliu0
- 🌙 中秋福利续上!OpenCode 官方再延长一周!DeepSeek V4.1 Flash 的 4 倍额度已延至 9 月 27 日,完美覆盖中秋! — @NFT_Chen
- 🚨 Step 5 Preview — @chetaslua
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 18.9k posts from 4.9k X accounts over the last 21 days, 2.1k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 06:12 UTC. Full method.