Hello fellow datanistas!
Have you ever wondered how to efficiently build composite bots for language model applications? Or perhaps you've been curious about the Mixin pattern in Python and how it can be used to create more modular and composable classes? If so, I have just the blog post for you!
In the post, I discuss the recent improvements I've made to LlamaBot, a project I've been working on in my spare time (or whatever I can squeeze out). I discuss the changes I've made, the motivations behind them, and the insights I've gained along the way. I believe this post could be useful for those of you interested in machine learning + engineering, as it provides a practical example of how to approach complex problems with patience and a desire to understand every detail. Give it a read and share it with anyone you think might benefit from it! You can find the post here.
As always, I appreciate your support and look forward to hearing your thoughts. Happy reading!
Cheers,
Eric