Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
1. Introduction to Spring AI
- Creating and configuring projects
- The significance of prompts and submission mechanisms
- Developing initial tests
- Selecting appropriate models
- Configuring model parameters
- Overview of Spring AI capabilities
2. Understanding responses
- Validating the relevance of answers
- Evaluating runtime accuracy
3. Prompt in details
- Utilizing prompt templates
- Crafting custom prompt templates
- Comprehending context
- The function and importance of roles
- Guiding response generation via options
- Streaming and output formatting
- Interpreting response metadata
4. Using your data and documents
- Grasping the concept of RAG (Retrieval-Augmented Generation)
- Initializing vector stores and ingesting documents
- Implementing basic RAG functionality
- Applying RAG with advisors
- Leveraging modular RAG features
5. The role of memory in AI
- The necessity of memory in AI systems
- Integrating and configuring memory for conversational continuity
- Managing conversation IDs
- Implementing persistent memory
- Persisting chat memory in vector stores
6. AI Tools
- Building applications with tool support
- Exploring tool capabilities
- Developing and deploying tools
- Using functions as tools
7. The Model Context Protocol (MCP)
- The rationale behind MCP
- Interacting with MCP Clients
- Developing MCP Servers
- Configuring databases and tools for MCP Servers
- Understanding HTTP and SSE (Server-Sent Events) transport
- Exposing prompts and resources
8. Monitoring operations
- Activating actuator metrics
- Monitoring vector store activities
- Analyzing model interactions
- Tracking token usage
- Implementing Prometheus integration and dashboard creation
- Tracing AI operations
9. Safeguarding in generative AI
- Restricting document access via RAG
- Securing tool execution
- Mitigating adversarial prompting
- Moderating user inputs
10. Common generative patterns
- Generating content summaries
- Translating messages
- Performing sentiment analysis
11. The role of the Agents
- Defining AI agents
- Implementing agentic workflows
- Chaining prompts, task routing, and parallelization
- Accessing agents via MCP
Requirements
Participants are expected to possess:
- Proficiency in Java programming
- Practical experience with Spring and Spring Boot
- Knowledge of constructing and setting up Spring Boot applications
- A foundational grasp of REST APIs and HTTP
- A basic understanding of JSON and application configuration
- A fundamental awareness of generative AI and Large Language Models (LLMs)
- Recommended familiarity with database and data access principles
- No prior background in Spring AI, RAG, MCP, or AI agents is necessary
21 Hours
Testimonials (1)
Detailed information provided on the more advanced topics requested.
