网页截图比文本更适合喂给大模型检索，这个结论我第一眼是不信的。看完伯克利这个团队的 README，觉得他们有道理。
This is a AI post classified by Jev as RAG & memory (a tool drop), kept by the AI Radar because it carries real work, not commentary.
网页截图比文本更适合喂给大模型检索，这个结论我第一眼是不信的。看完伯克利这个团队的 README，觉得他们有道理。 给模型喂网页，常规做法是先解析成文字再切块，表格、图表、版式在这一步就丢了，后面模型答不上来是因为它根本没看见。 PixelRAG 反过来，把网页、PDF 直接渲染成一张张截图，在图上做检索，答案在表格里就把那块截图原样递给模型读。 已斩获 10000+ GitHub Star！ GitHub：http://github.com/StarTrail-org/PixelRAG 他们把整个维基百科 828 万个页面建好了索引挂在线上，不用配置不用密钥，可以直接调，拿一张图当查询条件也行。 还顺手出了一个 Claude Code 插件，叫 pixelbrowse，Claude 看网页时截一张图自己读，不去抓源码，图表和布局跟人看到的一样。 想给自己的文档建索引也行，Mac 的 M 系列芯片上一份 PDF 三分钟左右建完，不用显卡。
Posted by GitHubDaily (84.6k followers) 1 h ago · 1 likes · 681 views · view the original post on X. Kept by the AI Radar as RAG & memory. Tools mentioned: pixelrag.
More AI work like this
- This might be the first open-source memory architecture to cover associative recall. The… — @TencentAI_News
- Wow Jev as a top-k reranker works pretty damn well🤯 — @zainhas
- this is straight f*cking gold — @polydao
- it's awesome to see the reception here 🔥 — @jerryjliu0
- Introducing DocJev - a lightning-fast OSS library for document classification and… — @jerryjliu0
- Introducing DocJev - a lightning-fast OSS library for document classification and… — @jerryjliu0
- Building a 3D model of Level 78 of the WTC South Tower - the site of some of the worst… — @DrewPavlou
- Jav seems to be quite good at semantic search beating gemini-lite agentic-retrieval at… — @_can1357
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. 38.1k posts from 4.9k X accounts over the last 14 days, 1.6k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 08:26 UTC. Full method.