GenAI for Busy Java Developers (Video Course)

Description

Java software engineers who need to learn how to harness the capabilities of generative AI tools for critical aspects of the production software process.

This video course empowers Java engineers with the basic knowledge and skills needed to harness the capabilities of generative AI tools for various aspects of the production software process.

Developed for beginner and early intermediate Java developers, it explores the impact of Machine Learning on the Java ecosystem and features hands-on coding using tools such as OpenAI ChatGPT, Google Gemini, Anthropic Claude, and other GenAI services using the LangChain4j API. With a focus on practical applications, participants will gain proficiency in GenAI, an understanding of context, learn about embeddings, and how to responsibly integrate GenAI into Java applications.

Attendees will:

• Learn the skills they need in order to apply generative AI to real-world software development. Enterprise developers will learn the fundamentals of generative AI and how to best apply them to reliably put GenAI applications into production.
• Understand programmatic interfaces to GenAI using REST APIs and featuring the LangChain4J Java API, including many source code examples covering different prompt techniques, streaming, embeddings, templates, context, Retrieval-Augmented Generation (RAG) and an introduction to agents
• Architect and implement a basic chatbot application that understands private document sets.

Skill Level:

• Beginner to Early Intermediate

Learn How To:

• Differentiate between the two basic types of deep learning
• Structure prompts and select techniques that produce useful output
• Use LangChain4j to create a working GenAI application
• Apply embeddings to various use cases
• Manage context for effective LLM responses
• Choose an appropriate vector database and what to store in that database
• Create tools and understand the basics of agents

Course Requirement:

• Basic Java knowledge

Who Should Take This Course:

• Java developers who manage production deployment and need to understand how to apply generative AI in their daily workflow
• Programmers with modern software development responsibilities who need to use AI tools for code creation or to create applications that leverage GenAI services

About Pearson Video Training:   

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Prentice Hall, Sams, and Que. Topics include IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at  http://www.informit.com/video.

Video Lessons are available for download for offline viewing within the streaming format. Look for the green arrow in each lesson.

Sample Content

Table of Contents

Lesson 1: Discover AI Origins, Patterns, and AI/ML Taxonomy

1.1 Describe the historical evolution of patterns, AI and Machine Learning

1.2 Explain the distinction between GenAI and PredAI

1.3 Identify common patterns used in software development
 

Lesson 2: Learn about Neural Networks, Weights, and LLMs

2.1 Illustrate the structure of a basic neural network 

2.2 Explain the role of weights in the learning process

2.3 Define GenAI terminology

2.4 Describe the training process and the stochastic nature of GenAI models

2.5 Compare traditional deterministic programming to probabilistic GenAI models

Lesson 3: Use Prompt Engineering and Context

3.1 Design effective prompts using zero-shot, few-shot, and chain-of-thought techniques

3.2 Explain the importance of context in prompt success and result consistency

3.3 Explain Context Window and the stateless nature of an LLM connection

3.4 Compare various message roles: System, User, and Assistant

3.5 Describe a useful prompt structure for handling context

Lesson 4: Learn GenAI APIs for Java Developers REST and Java APIs

4.1 Describe various types of programmatic access to GenAI services

4.2 Compare various REST calls from popular GenAI providers 

4.3 Demonstrate REST calls and message components

4.4 Explain the history of LangChain4j

4.5 Identify why an abstract API is useful for Java developers

4.6 Demonstrate simple LangChain4j examples

Lesson 5: Discover LangChain4j Basics

5.1 Define core components of LangChain4j

5.2 Install and configure LangChain4j in a Java project using Gradle/Maven

5.3 Demonstrate how to send UserMessages and SystemMessages to an LLM

5.4 Implement a basic chatbot with prompt context

5.5 Demonstrate incorporating external data as context for the chatbot

5.6 Apply memory to retain conversation state

5.7 Implement a basic chatbot using ChatMemory

Lesson 6: Use Prompt Templates

6.1 Identify why templates are useful 

6.2 Create reusable prompt templates using LangChain4j

6.3 Demonstrate dynamic prompt composition using Java variables

6.4 Identify the advantages and disadvantages of prompt templates
 

Lesson 7: Understand Chatbot Architecture

7.1 Diagram the structure of a chatbot architecture

7.2 Identify roles of System, User, and Assistant messages with a chatbot

7.3 Explain the use of LangChain4js AiService

7.4 Assess chatbot context and costs

7.5 Demonstrate a chatbot that maintains conversational context

Lesson 8: Learn Retrieval Augmented Generation (RAG)

8.1 Understand basic ways to get an LLM to return a useful result

8.2 Explain the motivation and architecture behind RAG

8.3 Illustrate the document retrieval and injection pipeline

8.4 Identify the advantages of a RAG-based system

8.5 Identify potential issues and failure modes of retrieval-based systems

Lesson 9: Understand Embedding Vectors and Similarity

9.1 Understand why similarity is needed for GenAI

9.2 Define embeddings and their mathematical representation

9.3 Compare 2d, 3d, and N-d embeddings

9.4 Demonstrate how to generate a text embedding

9.5 Describe LangChain4js EmbeddingModel

9.6 Compute similarity between vectors to rank text relevance

Lesson 10: Learn about Vector Stores

10.1 Describe why Vector Stores are needed

10.2 Classify different vector store options

10.3 Understand the importance of a chunking strategy 

10.4 Describe LangChain4js EmbeddingStore and Data Ingestion architecture

10.5 Construct an index and search over it using embedding similarity
 

Lesson 11: Understand the Basics of Agents

11.1 Identify what a Tool (function-calling) is

11.2 Understand the relationship between reasoning models and tools

11.3 Demonstrate Tool use with AiService

11.4 Define what an Agent is

11.5 Describe current frameworks and the state of the art of Agents

Lesson 12: Recap and Next Steps

12.1 Summarize major concepts from each chapter

12.2 List tools, libraries, and resources used in the course

12.3 Reflect on where GenAI best fits into Java development workflows

12.4 Identify advanced areas for deeper study 

Updates

Submit Errata