Darling Data/Get AI-Ready With Erik

  • $500

Get AI-Ready With Erik

  • Course
  • 31 Lessons

Vector search is landing in your SQL Server whether you invited it or not. You don't have to know how it works - you just have to know how to work with it. Learn semantic search, embeddings, VECTOR types, DiskANN indexes, and RAG using real StackOverflow data. No AI hype, no toy examples - just practical patterns from first query to production. Get AI ready without the nonsense.

Contents

Course Introduction

Get your bearings and learn what you're gonna learn about.

Prerequisites - 10 minutes
Course Introduction - 11 minutes
Resources.zip
README.md

Part 1: Foundations and Fundamentals

Look, you've heard "AI" ten million times lately. You're tired. I'm tired too.

But vector search is happening whether you like it or not.

Good news: you don't need to understand the math or train models. You just need to know how SQL Server stores these things and how to query them.

That's what this section does.

SQL Server 2025 GA: What Shipped and What Didn't - 24 minutes
What Embeddings Actually Are - 20 minutes
Exploring StackOverflow2010 - 18 minutes
The VECTOR Data Type - 25 minutes
Generating Our First Embeddings - 15 minutes
VECTOR_DISTANCE in Practice - 28 minutes
Searching with User Queries - 11 minutes

Part 2: Practical Search Applications

This is where it gets useful. No more theory - you're building actual features people will use. "Show me similar questions" without writing a nightmare LIKE clause. "Find related answers" without manually tagging everything. The kind of stuff product managers ask for and you can actually deliver.

Finding Related Content - 14 minutes
Cross-Table Vector Search - 13 minutes

Part 3: Hybrid Search

Here's the truth: vectors are great until someone searches for "SQL-DMV-1234" and your semantic search returns philosophical discussions about database monitoring. Sometimes you need exact matches. Sometimes you need meaning. Usually you need both. Learn when to use what and how to combine them without creating a Frankenstein query.

When Keyword Search Wins - 13 minutes
Combining Keyword and Semantic Search - 15 minutes
Combining Search Signals (RRF + Weighted Scoring) - 24 minutes

Part 4: Vector Indexes (Preview)

Scanning a million vectors works exactly once before someone asks why the query takes 30 seconds. Enter vector indexes - specifically DiskANN. The good news: massive speedup. The bad news: it's still in preview. Learn what works, what doesn't, and what "approximate" actually means for your results. It's probably fine.

Why Approximate Search Matters - 11 minutes
CREATE VECTOR INDEX - 12 minutes
VECTOR_SEARCH Function - 12 minutes
DiskANN Behavior - 16 minutes
Preview Limitations - 12 minutes

Part 5: SQL Server Native Integration

Microsoft finally made it so you don't need Python scripts running somewhere. AI_GENERATE_EMBEDDINGS lets you create vectors from T-SQL like a civilized person. Point it at OpenAI, Azure, or your local Ollama instance and suddenly embeddings are just another column. This is the "it just works" part of the course.

CREATE EXTERNAL MODEL - 13 minutes
AI_GENERATE_EMBEDDINGS - 11 minutes

Part 6: Embedding Management

Congratulations, you have embeddings. Now someone updates a record and your vectors are stale. Or someone pastes the entire Lord of the Rings into a text field and your model chokes. Welcome to production. Learn to handle updates without regenerating everything, chunk long content without losing meaning, and build triggers that won't make you hate your life.

Keeping Embeddings Current - 15 minutes
Long Content Strategies - 24 minutes

Part 7: Production Patterns

You know what's fun? Getting paged at 2am because vector search is slow and you have no idea why. You know what's better? Actually understanding execution plans for VECTOR_DISTANCE, knowing what metrics matter, and having monitoring in place. This is the DBA section - the part where you learn to keep vector search running when it counts.

Execution Plans for Vector Queries - 24 minutes
Vector Search Observability - 13 minutes
Capacity Planning - 13 minutes

Part 8: Advanced Patterns

RAG is everywhere now - feeding LLMs relevant context from your data so they don't hallucinate. Turns out SQL Server makes a perfectly good knowledge base for it. Learn to search across multiple tables, format results for LLM consumption, and build the kind of AI features everyone's talking about.

RAG with SQL Server - 14 minutes
Advanced Searching Across Tables - 9 minutes

Part 9: Goodbye Forever

I'm terrible at goodbyes, but this is the last video (at least until Cumulative Updates start coming out).

This video is about where to go and what to do when you finish and actually know what you're doing.

Where to Go From Here - 15 minutes