How AI Is Built

#003 AI Inside Your Database, Real-Time AI, Declarative ML/AI

14 snips
Apr 19, 2024
Learn how SuperDuperDB simplifies AI integration into databases, enabling real-time computation for instant data updates. Explore the benefits of embeddings and classifications, future plans for AI-powered databases, and the framework for configuring AI workflows. Discover the challenges in computing embeddings, handling text chunks, declarative machine learning, real-time feature calculation, and advancements in model deployment.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
INSIGHT

AI Runs In Your Database

  • SuperDuperDB applies AI directly to your existing database to avoid heavy ETL and separate infrastructure.
  • That keeps the data deployment as the source of truth and reduces manual pipeline work.
ADVICE

Compute Inference After Insert

  • Calculate embeddings (or other inferences) after insertion by watching the database instead of during data ingestion.
  • This ensures vectors or predictions stay real-time and consistent for all clients inserting data.
INSIGHT

Vectors Are Not The Whole Search Problem

  • Pre-computing vectors is only part of search; updating indexes and data-facing preprocessing matter equally.
  • Bringing AI and databases closer leverages existing DB expertise to handle incremental updates and filtering.
Get the Snipd Podcast app to discover more snips from this episode
Get the app