Spring AI Training Course

1. Introduction to Spring AI

• Project creation and configuration
• The role of prompt and prompt submission
• Writing a first test
• Choosing a model
• Model configuration
• Preview of Spring AI capabilities

2. Understanding responses

• How to check for relevant answers
• The accuracy at runtime

3. Prompt in details

• Using prompt templates
• Defining a new prompt template
• Understanding context
• The role and its importance
• Influencing response generation using options
• Streaming and formatting the output
• The metadata in response

4. Using your data and documents

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

5. The role of memory in AI

• Why do we need memory
• Adding and configuring memory to support conversation
• The conversation ID
• Support persistent memory
• Storing chat memory in vector store

6. AI Tools

• An application tools-enabled
• Understanding tools capabilities
• Writing and putting the tool to work
• Functions as tools

7. The Model Context Protocol (MCP)

• Why do we need MCP?
• Working with an MCP Client
• Writing the MCP Server
• Database and tools for the MCP Server
• Understanding HTTP and SSE (Server-Sent Events) transport
• Exposing prompt and resources

8. Monitoring operations

• Enabling actuator metrics
• Checking for vector store operations
• Looking for model interaction
• Token counting
• Putting all in Prometheus and creating a dashboard
• Tracing AI operations

9. Safeguarding in generative AI

• Controlling document accessed via RAG
• Securing tools
• Contrasting adversarial prompting
• Moderating user input

10. Common generative patterns

• Content summarization
• Message translation
• Sentiment analysis

11. The role of the Agents

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