This course taught prompt engineering and working with data for the first wave of LLMs. It is now sorely out of date.
From language model prompts to prototype in three days.
Online book at rastringer.github.io/promptcraft/
PromptCraft is a course to take developers from language model prompting to a prototype application using
Google Cloud’s Generative AI Studio in three days. The material is also easily ported to other large language models with a few code changes.
LLMs and Generative AI have revolutionised the field of machine learning. The power of the foundational models, prompt tuning and model adaption mean practitioners can achieve what used to take weeks or months in a matter of days.
Day one covers how to use clever prompting to categorize data, give effective responses grounded in data, validate, keep safe and evaluate outputs.
Day two includes an introduction to Langchain, a popular library for interacting and building applications with LLMs, embedding data such as PDF reports or a product catalog, then retrieving accurate responses, summaries and answers.
Day three is a hackathon, where participants choose a use case, bring or create (via an LLM!) some data, and create a proof-of-concept application.
All lessons are launched via Colab. The course only requires the free tier to complete. There will be some (minimal, excluding the hackathon which will vary depending on the project) Google Cloud costs.
Prerequisites
-
A Google Cloud account.
-
A Google Cloud project with billing enabled.
-
Familiarity with programming in Python.