SchemaWright
LearnExercisesLecturesPricing
lectures/Data for AI and machine learning

Machine learning in production

Track 4 of 5 · Data for AI and machine learning · 10 of 10
  1. 1. Embeddings as data (in preparation)
  2. 2. Vector indexes (in preparation)
  3. 3. Search before vectors (in preparation)
  4. 4. The database behind RAG (in preparation)
  5. 5. The database behind a chat app (in preparation)
  6. 6. Recommendation data (in preparation)
  7. 7. Memory for AI agents (in preparation)
  8. 8. Training data (in preparation)
  9. 9. Feature stores (in preparation)
  10. 10. Machine learning in production (in preparation)
← PreviousNext →
In preparationLecture IV.10

The question it answers

What do the systems large companies published say about the data around a model?

This lecture is being written. Like every lecture here, each claim in it is read in its primary source and cited to the page before it is published. See what you can read now.

Track 4 of 5 · Data for AI and machine learning · 10 of 10
  1. 1. Embeddings as data (in preparation)
  2. 2. Vector indexes (in preparation)
  3. 3. Search before vectors (in preparation)
  4. 4. The database behind RAG (in preparation)
  5. 5. The database behind a chat app (in preparation)
  6. 6. Recommendation data (in preparation)
  7. 7. Memory for AI agents (in preparation)
  8. 8. Training data (in preparation)
  9. 9. Feature stores (in preparation)
  10. 10. Machine learning in production (in preparation)
← PreviousNext →

Write the schema.
Let the tests decide.

Business scenarios, answered in DDL, graded by hidden tests on a real Postgres.

Start for free See the plans
SchemaWright

Database design, practised.
Graded on a real Postgres.

devgabmasantos@gmail.com

Practise

  • Lessons
  • All exercises
  • The first exercise
  • Pricing
  • Sign in

Tracks

  • Fundamentals
  • Deletion & History
  • Multi-tenancy
  • Time
  • Normalization
  • Performance
© SchemaWright. All rights reserved.Privacy policyTerms of service
!