Geir's notes

Feb 19, 2025

LLM codegen workflow

Enjoyed this blog post by Harper Reed (via) where he discusses his workflow involving the usage of Language Learning Models (LLMs) in code generation.

Feb 16, 2025

Counting Tokens: Will My Text Fit into AI's Memory?

I count the tokens in a blog post, the complete works of Shakespeare, and the 500k+ emails from the Enron scandal and ask, is RAG dead?

Feb 9, 2025

Command Line Tool for Code Reviews with an AI Model Running Locally

Since I am too impatient to wait for access to CoPilot powered code reviews, I wrote a command-line tool that fetches pull requests from GitHub and code reviews them with AI.

Feb 8, 2025

Searching PDF documents using LLMs with RAG

Embeddings can be used to search documents with results that reflect the meaning of your search rather than the actual search words and terms. In this post, I implement a RAG search with the help of LangChain and embeddings.

Feb 1, 2025

Chat with Deepseek on your Mac via the browser

LLM models that run on your local machine are becoming better and better. Indeed, thanks to the AI arms race, these models will soon be good enough for many tasks required by individuals and companies looking to leverage AI. I’ve already covered how to install an LLM locally using Ollama, but how do you chat with the model in a browser? Enter WebUI.

Jan 26, 2025

Running Hugging Face models in Ollama

I’m a big fan of Ollama, the easiest way to run LLMs on my Mac. Ollama integrates nicely with Hugging Face, the GitHub of LLMs, so it can be very easy to run a model published on Hugging Face with Ollama.

Jan 25, 2025

Comparing AI embedding models

In my last post I used Facebook’s Llama for creating vector embeddings from different words and sentences. My editor, ChatGPT of course, suggested I use a model that specializes in embedding rather than Llama, which does text generation (chatting). I did, and the results are a bit surprising.

Jan 19, 2025

Understanding AI embeddings - how machines see language

Embedding is the concept of representing words, concepts, and sentences so that computers can understand them. It’s fundamental to LLMs, and it also underpins things like semantic search, Netflix recommendations, and Google translate. I want to play around with embeddings a bit to see how they work and how they can be used.

Jan 21, 2024

Predicting outcomes for passengers on the Titanic with deep learning

The passenger list on the Titanic is a popular dataset for machine learning, so I thought it was a fitting way to start this documentation of my AI experiements.