Build an LLM and RAG-based Chat Application with AlloyDB and Agent Platform

Este exercicio faz parte do curso

Create Generative AI Apps on Google Cloud

Instruções do exercicio

In this lab, you create a chat application that uses Retrieval Augmented Generation, or RAG, to augment prompts with data retrieved from AlloyDB.

Este exercicio faz parte do curso

Create Generative AI Apps on Google Cloud

IntermediárioNível de habilidade

0.0+

Comece o curso gratuitamente

In this module, you learn about generative AI applications, and types of applications that can use the power of generative AI. You also learn about foundation models provided by Google, and challenges that exist when using generative AI in your applications.

Exercise 1: Getting started Exercise 2: Introduction to generative AI applications Exercise 3: Foundation models Exercise 4: Challenges of Gen AI for applications Exercise 5: Summary Exercise 6: Quiz Question 1 Exercise 7: Quiz Question 2 Exercise 8: Quiz Question 3 Exercise 9: Quiz Question 4 Exercise 10: Quiz Question 5 Exercise 11: Quiz Question 6 Exercise 12: Quiz Question 7 Exercise 13: Quiz Question 8

In this module, you learn about generative AI prompts. A prompt is a natural language request submied to a language model to request a response back. You can design your prompts to improve the results being returned from a model.

Exercise 1: Getting started Exercise 2: Introduction to prompts Exercise 3: Prompt structure Exercise 4: Prompt engineering Exercise 5: Summary Exercise 6: Quiz Question 1 Exercise 7: Quiz Question 2 Exercise 8: Quiz Question 3 Exercise 9: Quiz Question 4 Exercise 10: Quiz Question 5 Exercise 11: Quiz Question 6 Exercise 12: Quiz Question 7 Exercise 13: Quiz Question 8

In this module, you experiment with Vertex AI Studio, which provides tools to rapidly prototype, tune models with your own data, and seamlessly deploy to applications. You explore multimodal capabilities of Gemini, design prompts, and generate conversations.

Exercise 1: Get Started with Agent Studio

In this module, you learn how to improve the accuracy of foundation models. You learn about retrieval augmented generation, or RAG, a technique for grounding a foundation model with external sources of knowledge. You'll also see an example RAG-capable generative AI solution architecture on Google Cloud.

Exercise 1: Getting started Exercise 2: Improving foundation model accuracy Exercise 3: Retrieval Augmented Generation (RAG)Exercise 4: Retrieving relevant data Exercise 5: RAG architecture using Vertex AI Exercise 6: Summary Exercise 7: Quiz Question 1 Exercise 8: Quiz Question 2 Exercise 9: Quiz Question 3 Exercise 10: Quiz Question 4 Exercise 11: Quiz Question 5 Exercise 12: Quiz Question 6 Exercise 13: Quiz Question 7 Exercise 14: Quiz Question 8

In this module, you build a chat application that uses large language models (LLMs) and retrieval augmented generation (RAG) to create engaging and informative conversations.

Exercise 1: Build an LLM and RAG-based Chat Application with AlloyDB and Agent Platform

Exercicio Atual

Link to lesson PDFs

Exercise 1: Course resources