Spring AI Training Course

1. Getting Started with Spring AI

• Setting up projects and configurations
• The function of prompts and submitting them
• Creating your initial test
• Selecting the appropriate model
• Configuring model parameters
• Overview of Spring AI features

2. Analyzing AI Responses

• Verifying the relevance of generated answers
• Assessing runtime accuracy

3. Advanced Prompting Techniques

• Utilizing prompt templates
• Creating custom prompt templates
• Comprehending the concept of context
• Understanding the significance of roles
• Guiding response generation through options
• Managing streaming and output formatting
• Examining response metadata

4. Integrating Your Data and Documents

• Grasping the fundamentals of RAG (Retrieval-Augmented Generation)
• Initializing vector stores and ingesting documents
• Developing an initial RAG implementation
• Implementing RAG with an advisor
• Exploring modular RAG functionalities

5. Implementing Memory in AI Systems

• The necessity of memory in AI
• Integrating and configuring memory for conversational support
• Managing Conversation IDs
• Enabling persistent memory
• Persisting chat memory in vector stores

6. Utilizing AI Tools

• Enabling tool support in applications
• Understanding tool capabilities
• Developing and deploying tools
• Using functions as tools

7. Implementing the Model Context Protocol (MCP)

• The rationale for adopting MCP
• Interacting with MCP Clients
• Developing an MCP Server
• Integrating databases and tools for the MCP Server
• Understanding HTTP and SSE (Server-Sent Events) transports
• Exposing prompts and resources

8. Operational Monitoring

• Activating actuator metrics
• Monitoring vector store operations
• Tracking model interactions
• Monitoring token usage
• Setting up Prometheus and building dashboards
• Tracing AI operations

9. Security and Safeguarding in Generative AI

• Restricting document access via RAG
• Securing AI tools
• Countering adversarial prompting
• Moderating user inputs

10. Standard Generative AI Patterns

• Summarizing content
• Translating messages
• Analyzing sentiment

11. The Role of AI Agents

• Defining an agent
• Building agentic workflows
• Chaining prompts, routing tasks, and parallelizing processes
• Accessing agents via MCP