JavaScript Conference 2023 (Warsaw & Online)
Learn from the BestMeet Gerard Sans
Gerard Sans
Developer Evangelist for Web and Cloud, UK
Talk
Creating a chatbot using MakerSuite, PaLM API and Angular
In this talk, you will learn how to build a chatbot from scratch using Google's latest Generative AI using MakerSuite, PaLM API and Angular.
MakerSuite is a tool to build the new wave of Generative AI applications using PaLM foundational models. MakerSuite makes it simple to engineer prompts, so that you can create and experiment with LLMs to create AI-enabled Apps within minutes. By using MakerSuite, we will prototype, validate, and refine our ideas. From here is as easy as, export your code and start building!
We will be introducing the PaLM APIs for Text and Chat to build the foundations of a Bard-like Assistant with advanced features like adding a rich-text-editor for prompts, ElevenLabs natural voices to speak out outputs, and rendering rich media for chat rendering markdown, code fences, MermaidJS diagrams and more!
About Gerard Sans
Gerard Helps Developers succeed in Artificial Intelligence and Web3; Former AWS Amplify Developer Advocate. He is very excited about the future of the Web and JavaScript. Always happy Computer Science Engineer and humble Google Developer Expert. He loves to share his learnings by giving talks, training and writing about cool technologies. He loves running Web3 London, GraphQL London, GraphQL San Francisco, mentoring students and giving back to the community.
Workshop
In this full day training, you will learn how to leverage Google's new Generative AI platform using MakerSuite and PaLM APIs (in beta) to build the next generation of AI-enabled Applications and powerful chatbots with Angular.
Topics we will cover:
1. Introduction to Generative AI, MakerSuite and PaLM 2
2. Common risks and mitigations: prompt attacks, biases and facts grounding.
3. Building a REST PaLM API client for Angular, Auth access and best practices around error handling
4. Using PaLM 2 for Text
5. Prompt techniques and how to use temperature, topK and topP
6. Lab: prompt design best practices
7. Using PaLM 2 for Chat
8. Introduction to LangChainJS, embeddings and vector databases
9. Lab: building a Bard clone
10. Foundational Models
11. Lab: adding code highlighting to our Bard clone
12. Bonus 1: Embeddings, LangChainJS and AI Agents
13. Lab: building an AI Agent with access to tools (calculator, search and runtime)
14. Responsible AI principles in practice: traceability and monitoring
15. Bonus 2: Eleven Labs latest Generative AI voices
16. Lab: adding realistic voices (v2) to our Bard clone (regular and streamed APIs)
Requirements:
- VPN access (VPN Express, or similar). Beta access only available in the US
- Intermediate Angular v16
- Basic knowledge of Node
Who is the target audience?
Anyone who wants to experiment with cutting edge Generative AI into their apps or websites using Angular. No previous experience with artificial intelligence is necessary.
Prompt guide
https://www.promptingguide.ai/course