Skip to content

Home
About
Claude Workflow
Build a RAG

Home
About
Claude Workflow
Build a RAG

AI & LLMs

Home
AI & LLMs

Posted inAI & LLMs Local News RAG - Prompts PHP Tutorials Prompt Engineering RAG Tutorial Series Retrieval-Augmented Generation

Bonus 2 — Local News RAG: Recency-Aware Answers & Multi-Source Citations

Posted by

By Tejas P Mehta July 25, 2026

The last piece Bonus 1 left us able to fetch, dedup, and retrieve today's news.…

Posted inAI & LLMs Evaluation & Deployment PHP Tutorials RAG Tutorial Series Retrieval-Augmented Generation

Episode 8 — Evaluating & Shipping

Posted by

By Tejas P Mehta July 23, 2026

From "seems good" to "measurably good" to "live" For two episodes I've been repeating the…

Posted inAI & LLMs Grounded Generation PHP Tutorials Prompt Engineering RAG Tutorial Series Retrieval-Augmented Generation

Episode 6 — Generation: Grounded Answers with Citations

Posted by

By Tejas P Mehta July 23, 2026

The last mile Five episodes of groundwork come together here. We can load documents, chunk…

Posted inAI & LLMs PHP Tutorials RAG Tutorial Series Retrieval Tuning Retrieval-Augmented Generation

Episode 5 — Retrieval: Top-K, Thresholds & Filtering

Posted by

By Tejas P Mehta July 23, 2026

Our search is fast, but it isn't smart After Episode 4, MySQL ranks our chunks…

Posted inAI & LLMs Document Chunking PHP Tutorials RAG Tutorial Series Retrieval-Augmented Generation

Episode 2 — Preparing the Knowledge Base: Loading & Chunking Your Docs

Posted by

By Tejas P Mehta July 23, 2026

Where we left off In Episode 1 we cheated. We pasted Nimbus's refund policy into…

Infographic comparing an LLM answering from memory versus an LLM using RAG to read from a knowledge base

Posted inAI & LLMs PHP Tutorials RAG Fundamentals RAG Tutorial Series Retrieval-Augmented Generation

Episode 1 — What Is RAG, and Why Should You Care?

Posted by

By Tejas P Mehta July 23, 2026

The problem, in one support ticket Imagine a customer opens a chat on Nimbus's website…