Home
Softono
sql-ai-datathon

sql-ai-datathon

Open source MIT Jupyter Notebook
Website GitHub
24
Stars
29
Forks
5
Issues
0
Watchers
3 months
Last Commit
Vector Databases Analytics & BI

About sql-ai-datathon

The SQL AI Datathon Starter Repository is a guided learning platform designed to equip developers with skills for building AI-powered applications using Microsoft SQL. This comprehensive training program consists of four structured missions that progress from foundational concepts to full-stack application development. Participants will learn to create vector embeddings, implement semantic and hybrid search capabilities, deploy Data API Builder endpoints, and orchestrate Retrieval Augmented Generation agents using C or Python. The curriculum covers essential technologies such as SQL Server 2025 AI features, Azure SQL Database free tier resources, and intelligent application patterns. After mastering the four core missions, users are invited to submit an Open Hack project for evaluation by experts. Judging criteria include problem understanding, innovation, technical execution, and real-world impact. Successful completion and competition entry can qualify participants for awards including a ticket to SQLCon 20

Platforms

Web Self-hosted

Languages

Jupyter Notebook

Links

Website Source Code
M
Published by
Microsoft
Visit View Profile

README.md

View on GitHub

SQL AI Datathon Starter Repository

Welcome to the SQL AI Datathon! You'll complete guided missions that will prepare you for building AI-powered applications with Microsoft SQL. You’ll use AI features to build embeddings, semantic/hybrid search, DAB endpoints, and an agent with RAG.

Complete all four missions to level up your skills, and add your own creative twist in the Open Hack to be eligible for judging for a ticket to SQLCon 2026!

Watch a live walkthrough of the missions on February 12th and 19th, 2026

Quick Start

  1. Fork this repo.
  2. Clone, or open in Codespaces.
  3. Complete all missions, 1-4.
  4. Learn how to submit an entry for the Open Hack project in open-hack.md.
  5. Submit your project by February 26 at 11:59 PM PT

Mission Briefs

  1. Embeddings & Search (folder)
  2. Retrieval Augmented Generation (RAG) (folder)
  3. Orchestrate SQL + AI workflows in C# or Python (folder)
  4. Building a Full-Stack AI Application in C# or Python (folder)
  5. Open Hack

What you’ll build

  • Embeddings & search
  • REST/GraphQL endpoints with Data API Builder
  • An agent that answers questions grounded in your SQL data

How you’re evaluated for the Open Hack

Criteria What Judges Look For
Problem Understanding Clear project type (Chatbot or Search), SQL as data source, proper RAG implementation
Innovation & Creativity Original approach, creative use of embeddings/semantic search, unique UX or data usage
Technical Execution Sound implementation, reproducible setup, focused scope, clear documentation
Insight & Impact Meaningful outcomes, depth of analysis, real-world applicability

Looking for some Inspiration?

Check out the Budget Bytes Series, where we build low cost AI applications with SQL: https://aka.ms/budgetbytes

Get started with SQL Today for Free

  • Azure SQL Database Free Tier:
    • Create up to 10 databases
    • 32 GB of storage and backup storage, per database
    • 100,000 vCore seconds, per database
    • Available for the lifetime of your Azure subscription

Resources