Using DuckDB for Embeddings and Vector Search
Machine learning, Scala, and interactive computing
Embeddings: What they are and why they matter
simonwillison.netEmbeddings are a really neat trick that often come wrapped in a pile of intimidating jargon. If you can make it through that jargon, they unlock powerful and exciting techniques …
Announcing Southbridge | Hrishi Olickel
Something worth building
Implement Semantic Search using Datasette
Spinning up 'vibe-search' on a SQLite Database.
You don't want to work with embeddings - Blog by Grzegorz Kossakowski
Embeddings are the assembly of the AI world. We should spare people touching them and climb the abstraction ladder as fast as possible. As we did in software.
Production RAG with a Postgres Vector Store and Open-Source Models
Explore Retrieval Augmented Generation (RAG) with Postgres Vector Store for sophisticated search functionalities in Django applications, leveraging the power of open-source models.
New Year's Resolutions for 2025
A year ago I posted my resolutions for 2024. I did it with no intention of making it an annual tradition, it was more to get it off my chest. However some friends recently made me reflect on the resolutions I have kept and those I haven't (that social pressure …
TomBot2000: automatically finding related posts using LLMs
How I used LLM embeddings to find related posts for my statically-generated blog and then used GPT4 to explain why they're similar.
Questions about the data to create LLMs for embeddings
Simon Willison has a fantastic article about using LLM embeddings in his October blog post: Embeddings: What they are and why they matter. The article is great, a perfect introduction, but I’…
Machine Learning Jargon | Abhishek Sundararajan
Books. What else?
Are They Actually Afraid of AI?
Principal AI Architect. Creator of open-strix, a harness for building agent teams. Writing about AI architecture, stateful agents, and what happens when you give AI memory.
Birb + Fossil: An RSS Revival?
Principal AI Architect. Creator of open-strix, a harness for building agent teams. Writing about AI architecture, stateful agents, and what happens when you give AI memory.
What shall we forget next?
We forget everything. What shall we make of that?
Using LLM Embeddings to Normalize User Data
How cosine similarity in embedding space can power high-quality normalization.
How do vector databases work?
Finding similar documents in large collections
Retrieval Augmented Generation (RAG) with Llama Index and Open-Source Models
An introduction into Retrieval Augmented Generation (RAG) using Llama Index and open-source models, exploring how these technologies are shaping the future of AI.