Curs de pregatire Spring AI

1. Introduction to Spring AI

• Setting up projects and configuration
• The function of prompts and submission processes
• Writing initial tests
• Selecting the appropriate model
• Configuring model parameters
• An overview of Spring AI capabilities

2. Analyzing responses

• Verifying the relevance of answers
• Evaluating accuracy during runtime

3. Prompting in depth

• Utilizing prompt templates
• Creating custom prompt templates
• Contextual understanding
• The significance of the role field
• Steering response generation via options
• Streaming and output formatting
• Interpreting response metadata

4. Leveraging your data and documents

• Concepts behind RAG (Retrieval-Augmented Generation)
• Configuring vector stores and ingesting documents
• Implementing basic RAG workflows
• Building RAG solutions using advisors
• Exploring modular RAG features

5. The impact of memory in AI

• The necessity of memory in AI systems
• Implementing and configuring memory for conversations
• Managing conversation IDs
• Enabling persistent memory
• Persisting chat history in vector stores

6. AI Tools

• Enabling tool capabilities in applications
• Understanding the scope of AI tools
• Developing and integrating tools
• Using functions as tools

7. The Model Context Protocol (MCP)

• Why MCP is essential
• Interacting with MCP Clients
• Developing MCP Servers
• Integrating databases and tools for MCP Servers
• Understanding HTTP and SSE (Server-Sent Events) transport
• Exposing prompts and resources

8. Operational monitoring

• Activating actuator metrics
• Monitoring vector store activity
• Observing model interactions
• Tracking token usage
• Visualizing data in Prometheus dashboards
• Tracing AI-specific operations

9. Security in generative AI

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

10. Standard generative patterns

• Summarizing content
• Translating messages
• Analyzing sentiment

11. The function of Agents

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