Hacker News Reader

bartdegoedeon Fine-tuning a small language model for RAG in a browser on a Mac

I fine-tuned Qwen3-0.6B so my 'ask my blog' feature would stop making things up, or make less up. Answers mostly got worse :-D. Model, dataset and code are open, and you can try it at bart.degoe.de/ask/. Happy to answer questions.

bartdegoedeon Semantic/Hybrid Search in the Browser

It’s gets much larger (there’s the potion-multilingual-128M model, distilled from bge-m3 which has like 100 languages), so it gets to ~120m range for the lookup table (4x smaller if you’d do int8 quantization, so you could get to to 30-35mb).

bartdegoedeon Semantic/Hybrid Search in the Browser

Chrome ships with one (https://news.ycombinator.com/item?id=43973502) but AFAICT it’s only used for history, there’s no api for it. There’s also an included LLM? https://www.thatprivacyguy.com/blog/chrome-silent-nano-insta...

bartdegoedeon Modernizing my "150-line" Python search engine

A few years ago I wrote a post about implementing tf-idf in 150 lines of python. The data source it relied on was removed (turns out Yahoo! isn't as relevant anymore).

bartdegoedeon The Loyal Wingman

Adventures with writing a novel with LLMs

bartdegoedeon Building a full-text search engine in 150 lines of Python code

Added an MIT license. Have fun :-)

bartdegoedeon Building a full-text search engine in 150 lines of Python code

The idea was to illustrate the concepts of an inverted index and tf-idf :-) I've built some stuff like this for a smaller project written in Python because it was Easier™ than spinning up an Elasticsearch cluster (ie it definitely didn't need to scale :-D)

bartdegoedeon Building a full-text search engine in 150 lines of Python code

Author here: you may want to check out something like Whoosh https://whoosh.readthedocs.io/en/latest/intro.html (it's like a clone of Lucene but in pure Python). I've used this to build some basic search for a small Python website and it was more than fast enough for my purposes :-)

bartdegoedeon Free SSL on Github Pages with a custom domain: Part 2 – Let's Encrypt

Mailinabox (https://mailinabox.email/guide.html#admin) uses it to get SSL certificates too; you can see it in action here https://github.com/mail-in-a-box/mailinabox/blob/master/mana...

bartdegoedeon Searching your Hugo site with Lunr.js

It will contain all content for pages that are live (in my case that's only 2 so far: http://bart.degoe.de/js/search/index.json), so your user will download all the content you want to have available for search on your site on page load, and then, depending on your index configuration, load more data in memory.

Lunr has an analysis pipeline that will generate a bunch of tokens for queries to match on, and you can do pretty much anything there.

It won't scale to thousands of pages, but I don't have thousands of them anyway :-)