Generative AI is being used to develop new products and services across multiple industries, such as personalised marketing communications, chatbots for interacting with customers, and virtual assistants. It can also be used to create chatbots that can answer customer questions and provide support.
On this course, you’ll explore the use of interactive multi-turn chat models using Gen AI Studio on Vertex AI and learn how to incorporate those models into your application using the PaLM API and client libraries. You’ll learn how to design and test chat prompts to ensure the best outputs for your applications and discuss how to choose parameters for the PaLM API to improve response quality for your use case.
This Interactive Chat for Applications Using Gen AI Studio course is available as a private training session that can be delivered via Virtual Classroom, at our training centre in The Shard, or at a location of your choice in the UK.
Who should attend:
This course is ideal for application developers who want to leverage Generative AI in their applications, and machine learning practitioners supporting the development of GenAI-powered applications.
What you'll learn:
By the end of this course, you will be able to:
- Understand Vertex AI generative AI options for your applications
- Explore Gen AI Studio to interact with foundation models
- Design and tune chat prompts for your Generative AI use cases
- Understand the effect of changing PaLM API parameters on model responses
- Implement the PaLM API into your applications using the Python SDK
To get the most out of this course, you should have a basic understanding of either programming in Python or leveraging APIs in applications.
Basic familiarity with Google Cloud and Vertex AI as covered in the Google Cloud Fundamentals: Big Data and Machine Learning course is also required.
- Vertex AI on Google Cloud
- Generative AI options on Google Cloud
- Introduction to the course use case (Interactive chat)
- Introduction to Gen AI Studio
- Available models and use cases
- Designing and testing prompts in the Cloud Console
- Data governance in Gen AI Studio
- Lab: Getting started with Vertex AI, Gen AI Studio's User Interface
- Why is prompt design so important?
- Zero-shot, one-shot and few-shot prompting
- Providing additional context and examples
- Best practices
- Lab: Prompt Design for Multi-turn Chat in Gen AI Studio
- Lab: Getting Started with the Vertex AI PaLM API & Python SDK
- Introduction to the PaLM API
- Utilising generative models using the Python SDK
- Understanding model parameters for multi-turn chat
- Lab: Use the PaLM API to add a chatbot to your application
- Revisit model parameters for chatbots
- Optimising model parameters for different use cases
- Model output and Responsible AI