---
format: "aidr-story-markdown/v1"
id: "4b9d2298903428756c5ac7b250cb351bc23f8bfe9731d126887ffe0696ae27da"
canonical_url: "https://aidr.today/4b9d2298?lang=en"
title: "Running RAG with a (small) language model in the browser"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-13T15:56:29.000Z"
category: "Products"
topics: ["llm","funding"]
source_urls: ["https://bart.degoe.de/rag-with-a-small-language-model-in-the-browser/","https://lobste.rs/s/nsjjo3/running_rag_with_small_language_model","https://www.techmeme.com/261014/p17"]
summary: "A personal blog now runs semantic search and a small language model directly in the browser."
---

# Running RAG with a \(small\) language model in the browser

> [Open the canonical story](<https://aidr.today/4b9d2298?lang=en>)

**Published:** 2026-10-13T15:56:29.000Z
**Category:** Products
**Topics:** llm, funding

## Summary

A personal blog now runs semantic search and a small language model directly in the browser\.

## Sources

- [Story source](<https://bart.degoe.de/rag-with-a-small-language-model-in-the-browser/>)
- [Discussion](<https://lobste.rs/s/nsjjo3/running_rag_with_small_language_model>)
- [Story source](<https://www.techmeme.com/261014/p17>)