— TUTORIAL SERIES —
Spring AI with Llama
Build LLM-powered Java applications by pairing Spring AI with self-hosted Llama models — from local setup to a working RAG chat feature.
Chapters
- 01Hello, Spring AI!→
- 02Core Concepts: Tokens, Messages, and the AI Abstraction→
- 03Running and Comparing Multiple Models with Ollama→
- 04Prompt Engineering: PromptTemplate and Dynamic Prompts→
- 05Structured Output: Asking the AI to Serve JSON Instead of Raw Text→
- 06Chat Memory: Multi-Turn Conversations→
- 07RAG: Retrieval Augmented Generation→
- 08Persistent Vector Store with PgVector→
- 09Graph RAG with Neo4j→
- 10Function Calling: Tool Use and Java Method Binding→
- 11MCP: Exposing an Existing REST API as Tools→
- 12Multimodality: Images and Text Together→
- 13Streaming API: Real-Time Token-by-Token Responses→
- 14Document Intelligence: PDFs, Word Docs, and Web Pages→
- 15Semantic Search: Finding Meaning, Not Keywords→
- 16AI Agents: Autonomous Workflows and Tool Chaining→
- 17Evaluation: Testing and Scoring AI Responses→
- 18Performance and Caching: Handling Scale Efficiently→
- 19Security and Safety: Protecting Your AI Application→
- 20Production Deployment: Docker, Observability, and Going Live→