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
• An overview of Spring AI capabilities

2. Interpreting responses

• Verifying the relevance of answers
• Assessing accuracy at runtime

3. Deep dive into prompts

• Utilizing prompt templates
• Defining new prompt templates
• Comprehending context
• The significance of roles
• Influencing response generation through options
• Streaming and formatting output
• Maintaining metadata in responses

4. Leveraging proprietary data and documents

• Comprehending RAG (Retrieval-Augmented Generation)
• Establishing vector stores and ingesting documents
• Implementing a basic RAG solution
• Implementing RAG with an advisor
• Modular RAG functionalities

5. The significance of memory in AI

• The necessity for memory
• Implementing and configuring memory for conversations
• Managing conversation IDs
• Enabling persistent memory
• Storing chat memory in vector stores

6. AI Tools

• Developing tool-enabled applications
• Understanding tool capabilities
• Writing and deploying tools
• Utilizing functions as tools

7. The Model Context Protocol (MCP)

• The need for MCP
• Interacting with 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. Monitoring operations

• Enabling actuator metrics
• Reviewing vector store operations
• Analyzing model interactions
• Counting tokens
• Integrating with Prometheus and building dashboards
• Tracing AI operations

9. Safeguarding generative AI

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

10. Standard 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
• Accessing agents via MCP