Microsoft Ship AI Agent Framework: Detailed Explanation with Examples
Microsoft unified Semantic Kernel and AutoGen into a single AI Agent framework. This article explains the architecture, how it works, and hands-on examples using Java/Spring AI.
Updating RAG Documents: Versioning Over Overwriting
When source documents change, directly overwriting in the vector store easily causes data inconsistency. This article guides a safe versioning process for RAG.
What is MCP (Model Context Protocol)? Explained for Java Devs
Learn MCP – the standard protocol for LLMs to communicate with external data/tools, with examples of writing an MCP server using Spring AI.
Why exhaustive search costs so much?: detailed explanation with examples (RAG)
Flat search in RAG runs in O(n) and is perfectly accurate, but expensive on large data. This article explains IVF, nprobe, and the recall/speed tradeoff through Java examples.
12 AI Papers That Changed Everything: Explained with Examples
A comprehensive overview of 12 foundational AI papers — from AlexNet to RAG — with Java code illustrating each core idea.
12 Claude Code Features: Detailed Explanation with Examples
A comprehensive guide to 12 core Claude Code features – from CLAUDE.md, Plan Mode to Subagents – with practical examples on a Spring Boot project.
AI Inference Engineering: Detailed Explanation with Examples
Learn how LLMs generate tokens one by one during inference, optimization techniques like KV cache, batching, quantization, and how to measure performance using Java/Spring Boot.
Embeddings for Semantic Search: Detailed Guide with Examples
Learn how embeddings turn text into vectors for semantic matching, applying RAG with a working Java example.
From Found Passages to Grounded Answers in RAG
Finding relevant passages doesn't mean you have an answer. This guide covers rerank pipelines, hybrid search, and grounding so LLMs can answer with evidence and gracefully refuse when data is insufficient.
Grab uses AI Agent to boost productivity: detailed explanation with examples
Analyze how tech teams like Grab apply AI Agents to code review, error triage and automate repetitive tasks, with working Java/Spring AI examples.
Hugging Face Hub: Finding and Using Models
Guide to finding the right model on Hugging Face Hub, reading model cards, and calling models from both Python and Spring Boot applications.
MCP vs RAG vs AI Agent: Detailed Explanation with Examples
Compare MCP, RAG, and AI Agent through definitions, architecture, and concrete Java code examples, helping you know when to use which.
Tokenizer in Hugging Face: Principles and How to Use in Java
Learn how Hugging Face Tokenizer works, how to integrate it into a Spring Boot application via DJL, along with concrete encode/decode examples and tests.
Top 20 AI Concepts in LLM: Detailed Explanations with Examples
Summary of 20 fundamental concepts when working with LLM — token, embedding, RAG, fine-tuning, agent... with easy-to-understand Java/Spring AI code examples.
Transformers Pipeline: Running NLP Models in a Few Lines of Code
Guide to using Hugging Face Transformers' pipeline() for sentiment analysis, NER, summarization... without needing deep understanding of model architecture.
Use AI to Save Hours for Dev: Detailed Explanation with Examples
Practical guide on how to use LLM to reduce time writing code, tests, docs in Spring Boot projects, with runnable examples.