Bill the Plumber

A long time back I read an article on NYT about how costly being polite to chat bots was for OpenAI, et. al.

When I first starting using Quarkus Langchain4j I ran into some issues because I didn’t fully understand how Quarkus managed chat memory with Langchain4j.

TLDR; Reduce callbacks to your LLM by immediately returning from tool invocations.

So, writing a hello world examples did not really help me to understand the limitations of LLMs.

Quarkus Playen 1.0.0 is released!

It took me a while to figure this out so I thought I’d share it.

You can take an existing Quarkus HTTP application and deploy it as a native executable (Graal build) to Azure Functions using the Custom Handler runtime provided with Azure Functions.

Last week I merged Quarkus Live Coding and Continuous Testing support for Lambda and it will be available in Quarkus 2.3.

I’ll start by introducing some flaim bait: PR REVIEWS ARE WORTHLESS!

Quarkus has a new JSON parser and object mapper called QSON.