Quick Start
Welcome to Pixeltable! In this tutorial, we will survey how to create tables, populate them with data, and enhance them with built-in and user-defined transformations and AI operations.
This guide will get you from zero to a working AI application in under 5 minutes. Learn more by looking at this tutorial on Github.
Create Your First Multimodal AI Application
Let’s build an image analysis application that combines object detection and OpenAI Vision.
Installation
Please refer to our installation section here.
Create Table Structure
This creates a persistent and versioned table that holds data.
Add Object Detection
Computed columns are populated whenever new data is added to their input columns.
Add OpenAI Vision Analysis
Pixeltable handles parallelization, rate limiting, and incremental processing automatically.
Use Your Application
The query engine uses lazy evaluation, only computing what’s needed.
What happened behind the scenes?
What happened behind the scenes?
Pixeltable automatically:
- Created a persistent table
- Downloaded and cached the ResNet model
- Orchestrated the OpenAI API call
- Created an efficient processing workflow
- Stored all results for future use
Key Features
Persistent Storage
All data and computed results are automatically stored and versioned. Your app state persists between sessions.
Computed Columns
Define transformations once, they run automatically on new data. Perfect for AI orchestration.
Multimodal Support
Handle images, video, audio, and text seamlessly in one unified interface.
AI Integration
Built-in support for popular AI services like OpenAI, YOLOX, Hugging Face, Label Studio, Replicate, Anthropic…
Custom Functions (UDFs)
Extend Pixeltable with your own functions using the @pxt.udf
decorator: