惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

J
Java Code Geeks
量子位
腾讯CDC
A
About on SuperTechFans
小众软件
小众软件
Microsoft Azure Blog
Microsoft Azure Blog
T
Tailwind CSS Blog
V
V2EX
B
Blog RSS Feed
H
Hackread – Cybersecurity News, Data Breaches, AI and More
GbyAI
GbyAI
Recent Announcements
Recent Announcements
Microsoft Security Blog
Microsoft Security Blog
博客园 - 叶小钗
罗磊的独立博客
宝玉的分享
宝玉的分享
WordPress大学
WordPress大学
大猫的无限游戏
大猫的无限游戏
IT之家
IT之家
V
Visual Studio Blog
D
DataBreaches.Net
博客园 - 三生石上(FineUI控件)
月光博客
月光博客
有赞技术团队
有赞技术团队

Lobsters

Lunacy | Red Vice CIFSwitch: a non-universal Linux local root vulnerability RIPE NCC session fixation: poaching logins with an Atlas probe GNOME 2.20 but its Web Components Agentic Search for Context Engineering – Leonie Monigatti Garnix is shutting down [not OC] akashina.tngl.sh/jjc Concerning Emacs (and Jazz) Nitpicking the shell history scene in ‘Tron: Legacy’ What's cooking on SourceHut? Q2 2026 The tenth OpenPGP email summit Package managers that package package managers Clojure on Fennel part three: parsing WordPress at 23 Finding Miscompiles for Fun, Not Profit GitHub - creusot-rs/creusot: Creusot helps you prove your Rust code is correct. Announcing Rust 1.96.0 | Rust Blog A Love Letter to Neovim sqlite AGENTS.md Am I a Bad Friend? CSS vs. JavaScript • Josh W. Comeau Erlang Ecosystem Foundation - Supporting the BEAM community A brief note about slot access cost in Common Lisp Keyboard latency probe Rethinking the GNOME clipboard issues Back to the Building Blocks’ Building Blocks Tech Notes: Theseus: translating win32 to wasm Fast is better than slow Content-addressed Rust builds (or, what kache actually caches) Canada’s Bill C-22 and the security cost of collecting more data
Intent to Prototype: Embedding API
groups.googl · 2026-05-27 · via Lobsters

Contact emails

ying...@chromium.org, m...@chromium.org, rei...@chromium.org, kenji...@chromium.org, dbo...@chromium.org

Explainer

https://github.com/explainers-by-googlers/embedding-api

Specification

No information provided

Summary

The Embedding API is a proposed Web Platform API that allows developers to generate high-dimensional vector representations (embeddings) of content directly on the user's device. 

By leveraging Chrome's on-device AI infrastructure and a shared on-device model, this API enables powerful semantic understanding features—such as semantic search, Retrieval-Augmented Generation (RAG), and content clustering. It eliminates the latency, cost, and privacy trade-offs of cloud services. Furthermore, compared to DIY client-side approaches, it provides significant user benefits (saving bandwidth and local storage by preventing each site from downloading its own massive model) and developer benefits (abstracting away complex model delivery and keeping WebAssembly/WebGPU frameworks up-to-date).

Blink component

Blink>AI>Embedder

Web Feature ID

Missing feature

Motivation

While existing web technologies like WebAssembly and WebGPU provide standardized, high-performance, and privacy-preserving execution environments, deploying an embedding model still forces developers into a difficult trade-off: 

  • WebAssembly/WebGPU (DIY): Leads to significant storage and memory bloat, as every site must download its own multi-hundred megabyte model. 
  • Cloud APIs: Introduce network latency, financial costs for developers, and require sending potentially sensitive user text to third-party servers. 

By ensuring stateless execution and explicitly not persisting embeddings globally, an on-device API allows the browser to safely share a single, optimized model across all origins, drastically reducing the resource footprint while providing a simple, high-level JavaScript primitive for generalist developers. 

Key Use Cases

  • Semantic Search: Enable note-taking or documentation apps to find content based on meaning rather than keywords, entirely offline and private. 
  • On-Device RAG: Power local Q&A bots that retrieve relevant context from a user’s own data.
  • Real-time Content Intelligence: Provide proactive moderation hints or content categorization as a user types, before content is ever transmitted to a server.

Anticipated questions
Here's a list of problems that we want to discuss with other browser vendors and the Web Machine Learning Community Group (WebML CG) as part of Standards to ensure interoperability (Note: the explainer lists more in the "Ensuring an Interoperable API Design" section)

  • Model and Space Choices: Exploring requirements for open-weight models and allowing developers to specify or provide their own models, to ensure compatibility with server-side embedding databases.
  • Content Mediation: Can we develop some sort of mediation when embeddings must be used server-side?

Initial public proposal

https://github.com/webmachinelearning/proposals/issues/18

Requires code in //chrome?

True

Tracking bug

https://crbug.com/428233906

Estimated milestones

No milestones specified

Link to entry on the Chrome Platform Status

https://chromestatus.com/feature/5115796490682368?gate=5187435874091008