Learn to automate immediate engineering and unlock important efficiency enhancements in your LLM workload
Automated Immediate Engineering (APE) is a way to automate the method of producing and refining prompts for a Massive Language Mannequin (LLM) to enhance the mannequin’s efficiency on a selected process. It makes use of the thought of immediate engineering which entails manually crafting and testing numerous prompts and automates the whole course of. As we are going to see it’s very much like automated hyperparameter optimisation in conventional supervised machine studying.
On this tutorial we are going to dive deep into APE: we are going to first take a look at the way it works in precept, a few of the methods that can be utilized to generate prompts, and different associated methods comparable to exemplar choice. Then we are going to transition into the hands-on part and write an APE program from scratch, i.e. we received’t use any libraries like DSPy that can do it for us. By doing that we are going to get a a lot better understanding of how the rules of APE work and are a lot better geared up to leverage the frameworks that can supply this performance out of the field.
