Spring AI Training Course

1. Introduction to Spring AI

• Project creation and configuration
• The role of prompts and prompt submission
• Writing a first test
• Selecting a model
• Model configuration
• Overview of Spring AI capabilities

2. Understanding responses

• How to verify relevant answers
• Runtime accuracy

3. Prompt details

• Utilizing prompt templates
• Defining new prompt templates
• Understanding context
• The role of context and its importance
• Influencing response generation using options
• Streaming and formatting output
• Metadata within responses

4. Using your data and documents

• Understanding RAG (Retrieval-Augmented Generation)
• Setting up the vector store and loading documents
• A first RAG implementation
• Implementing RAG using an advisor
• Modular RAG capabilities

5. The role of memory in AI

• The need for memory
• Adding and configuring memory to support conversations
• Conversation IDs
• Supporting persistent memory
• Storing chat memory in a vector store

6. AI Tools

• Enabling tools in applications
• Understanding tool capabilities
• Writing and deploying tools
• Functions as tools

7. The Model Context Protocol (MCP)

• Why MCP is necessary
• Working with an MCP Client
• Writing the MCP Server
• Databases and tools for the MCP Server
• Understanding HTTP and SSE (Server-Sent Events) transport
• Exposing prompts and resources

8. Monitoring operations

• Enabling actuator metrics
• Checking vector store operations
• Monitoring model interactions
• Token counting
• Integrating with Prometheus and creating dashboards
• Tracing AI operations

9. Safeguarding in generative AI

• Controlling document access via RAG
• Securing tools
• Mitigating adversarial prompting
• Moderating user input

10. Common generative patterns

• Content summarization
• Message translation
• Sentiment analysis

11. The role of Agents

• Defining an agent
• Implementing agentic workflows
• Chaining prompts, task routing, and parallelization
• Agent access via MCP