Spring AI Training Course

1. Introduction to Spring AI

• Project creation and setup
• The significance of prompts and prompt submission
• Developing an initial test
• Selecting an appropriate model
• Configuring the model
• Overview of Spring AI features

2. Analyzing responses

• Verifying the relevance of answers
• Assessing accuracy during runtime

3. In-depth prompt engineering

• Utilizing prompt templates
• Creating a new prompt template
• Comprehending context
• Defining roles and their importance
• Guiding response generation through options
• Implementing streaming and output formatting
• Interpreting metadata within responses

4. Leveraging proprietary data and documents

• Grasping RAG (Retrieval-Augmented Generation)
• Configuring the vector store and ingesting documents
• Implementing a basic RAG solution
• Employing an advisor for RAG
• Utilizing modular RAG functionalities

5. The significance of memory in AI

• The necessity of memory systems
• Integrating and setting up memory for conversational support
• Managing conversation IDs
• Enabling persistent memory
• Storing chat memory within the vector store

6. AI Tools

• Creating tool-enabled applications
• Exploring tool capabilities
• Developing and implementing tools
• Using functions as tools

7. The Model Context Protocol (MCP)

• The rationale for MCP
• Interacting with an MCP Client
• Developing an MCP Server
• Integrating databases and tools for the MCP Server
• Comprehending HTTP and SSE (Server-Sent Events) transport
• Exposing prompts and resources

8. Monitoring operations

• Activating actuator metrics
• Making vector store operations
• Analyzing model interactions
• Performing token counting
• Integrating with Prometheus and building dashboards
• Tracing AI operations

9. Safeguarding in generative AI

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

10. Common generative patterns

• Summarizing content
• Translating messages
• Conducting sentiment analysis

11. The function of Agents

• Defining an agent
• Building agentic workflows
• Chaining prompts, task routing, and parallelization
• Accessing agents via MCP