Application Development with LLMs on Google Cloud (ADLGC) – Outline

Detailed Course Outline

Module 1 - Introduction to Generative AI on Google Cloud

Topics:

  • Vertex AI on Google Cloud
  • Generative AI options on Google Cloud
  • Introduction to course use case

Objectives:

  • Explore the different options available for using generative AI on Google Cloud.

Module 2 - Vertex AI Studio

Topics:

  • Introduction to Vertex AI Studio
  • Available models and use cases
  • Designing and testing prompts in the Google Cloud console
  • Data governance in Vertex AI Studio

Objectives:

  • Use Vertex AI Studio to test prompts for large language models.
  • Understand how Vertex AI Studio keeps your data secure

Activities:

  • Lab: Exploring Vertex AI Studio

Module 3 - LangChain Fundamentals

Topics:

  • Introduction to LangChain
  • LangChain concepts and components
  • Integrating the Vertex AI PaLM APIs
  • Question/Answering Chain using PaLM API

Objectives:

  • Understand basic concepts and components of LangChain
  • Develop LLM-powered applications using LangChain and LLM models on Vertex AI

Activities:

  • Lab: Getting Started with LangChain + Vertex AI PaLM API

Module 4 - Prompt Engineering

Topics:

  • Review of few-shot prompting
  • Chain-of-thought prompting
  • Retrieval augmented generation (RAG)
  • ReAct

Objectives:

  • Apply prompt engineering techniques to improve the output from LLMs.
  • Implement a RAG architecture to ground LLM models.

Activities:

  • Lab: Prompt Engineering Techniques

Module 5 - Creating Custom Chat Applications with Vertex AI PaLM API

Topics:

  • LangChain for chatbots
  • Memory for multi-turn chat
  • Chat retrieval

Objectives:

  • Understand the concept of memory for mult-iturn chat applications.
  • Build a multi-turn chat application by using the PaLM API and LangChain.

Activities:

  • Lab: Implementing RAG Using LangChain