Data Enrichment with LLMs for Obsidian: Better Tags

One issue I have using Obsidian is that I feel I don’t use enough of its feature set. I have lots of notes, but few are tagged particularly well, so it makes tags less useful overall. I would like to be able to make surprising connections and surface related items, which means imprecise tags are preferable to no tags, so false positives are less of a concern to me, and very low risk. ...

April 25, 2024 · 3 min · Eoin H

Retrieval-Augmented Generation Experiments (Part 1)

I’ve been researching LLMs, trying to find practical ways I can use them for myself, in my work or at home. One area that interests me is as tool to better understand the notes I’ve taken, topics I frequently learn about and areas I might want to explore more. I’m not the first to explore this territory (https://x.com/fortelabs/status/1749861644245848361). I’ll be looking at using a local model and building the system myself. I’m going to detail how I’ve built a toy system to chat with my notes. I’ll be using Ollama1 to serve an open-source model locally, and building the application using LangChain2 and StreamLit3. ...

February 14, 2024 · 6 min · Eoin H