Separating Storage From llm Embeddings

The llm program uses sqlite to store embeddings. I want to store my embeddings in PostgreSQL. Rather than try to alter the built-in storage, I opted for the more unix-friendly approach of simply printing the results to standard output. This was fairly easy to implement based on c…

Programming Throwdown

Jason Gauci and Patrick Wheeler have an excellent podcast called Programming Throwdown. I know Jason from the Austin CTO Club. The first episode I listened to taught me about something very useful that I had been looking for, namely GraphRAG models. Check it out!

A gh Alias For json Data

The GitHub command-line tool gh has a number of commands that can return json data. For example, this command returns the two fields of data for each repo: gh repo list --json field1,field2 But there is no way to fetch all fields without listing them explicitly. For commands that…

Canary Islands

Today I spoke with a Ukranian entrepreneur now living in the Canary Islands. I didn’t know the population of the islands exceeds 2 million! He told me a number of other things about the islands that were news to me. They experience Calima, sandstorms that blow in from the Sahara…

An llm Plugin Hack

The llm package from Simon Willison has a plugin architecture. So I decided to try it. Any reasonable person would begin with a new model plugin. I decided instead to create llm rag, an encapsulation of rag queries that otherwise requires a pipeline of invocations of both llm and…