Spring AI Training Course

1. Introduction to Spring AI

• Creating and configuring projects
• The significance of prompts and their submission
• Writing an initial test
• Selecting a model
• Configuring the model
• Overview of Spring AI features

2. Analyzing responses

• Verifying the relevance of answers
• Assessing runtime accuracy

3. Deep dive into prompts

• Utilizing prompt templates
• Creating new prompt templates
• Comprehending context
• The importance of roles
• Guiding response generation through options
• Streaming and formatting output
• Response metadata

4. Utilizing proprietary data and documents

• Grasping RAG (Retrieval-Augmented Generation)
• Configuring vector stores and ingesting documents
• Initial RAG implementation
• Implementing RAG with an advisor
• Modular RAG functionalities

5. The importance of memory in AI

• The necessity of memory
• Integrating and configuring memory for conversations
• Conversation IDs
• Implementing persistent memory
• Storing chat history in vector stores

6. AI Tools

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

7. The Model Context Protocol (MCP)

• The need for MCP
• Implementing an MCP Client
• Developing an MCP Server
• Databases and tools for the MCP Server
• Understanding HTTP and SSE (Server-Sent Events) transport
• Exposing prompts and resources

8. Operational monitoring

• Activating actuator metrics
• Monitoring vector store operations
• Tracking model interactions
• Token counting
• Integrating with Prometheus and building dashboards
• Tracing AI operations

9. Security in generative AI

• Controlling documents accessed via RAG
• Securing tools
• Defending against adversarial prompting
• Moderating user input

10. Standard generative patterns

• Summarizing content
• Translating messages
• Performing sentiment analysis

11. The function of Agents

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