In this module, we will explore the evolution of large language models, from their early stages to the present cutting-edge technologies. We will delve into the revolutionary impact of ChatGPT and similar models on modern AI, along with the benefits and challenges they present in various fields.

In this module, we will guide you through setting up Spring AI and integrating it with OpenAI to build AI-powered applications. You will get hands-on experience with tools like OpenAI’s Playground and develop a basic AI chat application with Spring’s ChatClient to interact with OpenAI's platform.

In this module, we will explore how GitHub Copilot can assist in error handling within your Spring Boot application. You’ll learn how to set up Copilot and implement custom error handling strategies to enhance code reliability and streamline development.

In this module, we will demonstrate how to streamline AI interactions using StringTemplates and PromptTemplates. You will learn how to construct flexible, dynamic prompts and customize message exchanges to optimize the efficiency of your AI-driven applications.

In this module, we will introduce Spring AI Advisors and show you how they can be used to enhance and modify AI interactions. You’ll learn to build a custom advisor, starting with a logging advisor, to improve your AI app’s debugging and monitoring capabilities.

In this module, we will dive deep into prompt engineering, teaching you how to craft clear and accurate prompts that lead to meaningful outputs. You will also explore real-world examples and learn techniques to mitigate potential risks such as prompt injection.

In this module, we will teach you how to generate structured outputs from LLMs using prompt engineering and Spring AI tools. You’ll gain hands-on experience in parsing structured data, essential for AI-powered applications that need consistent and organized information.

In this module, we will explore how tool calling can augment LLM functionality by integrating external systems. You will learn how to call live data like currency exchange rates and weather information, expanding the scope and accuracy of your AI-powered applications.

In this module, we will introduce Retrieval-Augmented Generation (RAG), a technique for providing LLMs with external knowledge. You’ll learn how RAG improves AI performance by integrating relevant, up-to-date information and explore its advantages over traditional methods like prompt stuffing.

In this module, we will walk you through building a full Q&A application powered by RAG. You’ll explore the process of indexing documents, retrieving relevant knowledge, and generating accurate answers, culminating in the development of an end-to-end AI solution.

In this module, we will teach you best practices for document ingestion within Spring AI. You’ll learn how to process various document types, including text and Word files, and use chunking techniques to structure content for better AI knowledge retrieval.

In this module, we will delve into the concept of multimodality, where AI can work across different data types. You will explore how OpenAI’s image models can generate visual content from text and learn to customize images based on input variations for better results.

In this module, we will show you how to analyze images using OpenAI’s vision API. You will learn to pass image files from your local system or as multipart data for processing, with real-world applications such as extracting data from invoices.

In this module, we will teach you how to work with OpenAI’s audio models, converting text to realistic speech and vice versa. You’ll explore the customization options for both text-to-speech and speech-to-text, providing you with the tools to build voice-enabled AI applications.

In this module, we will explore how to build local AI applications using Ollama and Spring AI. You’ll learn to set up your environment for running LLMs on your local machine and integrate Spring AI seamlessly, enabling you to develop AI-powered applications without relying on cloud services.