On this one-day course, you’ll explore the different tools and APIs on Google Cloud that you can use to integrate large language models (LLMs) into your application.
After taking a look at the generative AI options on Google Cloud, we’ll then explore LLMs and prompt design in Vertex AI Studio. Next, you’ll learn about LangChain, an open-source framework for developing applications powered by language models.
After a discussion around more advanced prompt engineering techniques, you’ll end the session by putting all your knowledge together to build a multi-turn chat application using LangChain and the Vertex AI PaLM API.
This Application Development with LLMs on Google Cloud course is available as a private session and can be delivered via Virtual Classroom, at our training centre in The Shard, London, or at a location of your choice in the UK.
Course overview
Who should attend:
This course is ideal for anyone who wants to understand the different options available for using generative AI on Google Cloud, and how LLMs can help when it comes to developing applications.
What you'll learn:
By the end of this course, you will be able to:
- Understand the different options available for using generative AI on Google Cloud
- Use Vertex AI Studio to test prompts for large language models
- Develop LLM-powered applications using LangChain and LLM models on Vertex AI
- Apply prompt engineering techniques to improve the output from LLMs
- Build a multi-turn chat application using the PaLM API and LangChain
Prerequisites
We recommend you first attend the Introduction to Developer Efficiency on Google Cloud course before taking this session.
Course agenda
- What is Generative AI?
- Vertex AI on Google Cloud
- Generative AI options on Google Cloud
- Introduction to course use case
- Vertex AI Studio
- Designing and testing prompts
- Data governance in Vertex AI Studio
- Lab: Getting Started with the Vertex AI Studio User Interface
- Introduction to LangChain
- LangChain concepts and components
- Integrating the Vertex AI Gemini APIs
- Question / Answering Chain using Gemini API
- Lab: Getting Started with LangChain on Google Cloud
- Review of few-shot prompting
- Chain-of-thought prompting
- Retrieval augmented generation (RAG)
- ReAct (reason, act)
- Lab: Prompt Engineering Techniques
- LangChain for chatbots
- Memory for multi-turn chat
- Chat retrieval
- Lab: Implementing RAG Using LangChain