bartdegoede
Re:Fine-tuning a small language model for RAG in a browser on a Mac
on Tuesday October 20, 2026 @09:07AM (#50165814)
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.
Fine-tuning a small language model for RAG in a browser on a Mac
Running RAG with a (small) language model in the browser
Narrating your blog with Kokoro, a local and open source text-to-speech model
Re:Semantic/Hybrid Search in the Browser
on Saturday July 11, 2026 @04:00PM (#48875295)
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).
Re:Semantic/Hybrid Search in the Browser
on Saturday July 11, 2026 @03:51PM (#48875217)
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...
Semantic/Hybrid Search in the Browser
Running a coding agent locally with MLX for when you hit your token cap
The Productivity Panic Is Your Problem Now
OpenClaw can book flights. But can it survive a dungeon crawl?
Building a semantic search engine in ±250 lines of Python
Building a semantic search engine in ±250 lines of code
Modernizing my "150-line" Python search engine
Re:Modernizing my "150-line" Python search engine
on Monday February 09, 2026 @03:02PM (#46950323)
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).
Migrating my hopelessly outdated Hugo blog with Claude Code
Re:The Loyal Wingman
on Tuesday October 21, 2025 @01:18PM (#45658481)
Adventures with writing a novel with LLMs
The Loyal Wingman
Tutorial: Predict diabetes using k-NN from scratch and using scikit-learn
Google, GitHub and others leverage conditional HTTP requests to build APIs
How to Make Reviewers Love Your Big Pull Requests
Creating and testing gRPC server interceptors in Ruby
Conditional HTTP GET: The fastest requests need no response body
Re:Building a full-text search engine in 150 lines of Python code
on Thursday March 25, 2021 @05:51PM (#26585899)
Added an MIT license. Have fun :-)
Re:Building a full-text search engine in 150 lines of Python code
on Thursday March 25, 2021 @03:19PM (#26584260)
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)
Re:Building a full-text search engine in 150 lines of Python code
on Thursday March 25, 2021 @02:26PM (#26583634)
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 :-)