document.addEventListener("DOMContentLoaded", function () {
  var script = document.createElement("script");
  script.type = "module";
  script.id = "runllm-widget-script"

  script.src = "https://widget.runllm.com";

  script.setAttribute("version", "stable");
  script.setAttribute("crossorigin", "true");
  script.setAttribute("runllm-keyboard-shortcut", "Mod+j");
  script.setAttribute("runllm-name", "Pixelbot");
  script.setAttribute("runllm-position", "BOTTOM_RIGHT");
  script.setAttribute("runllm-assistant-id", "256");

  script.async = true;
  document.head.appendChild(script);
});

Connect with the Pixeltable community and find support

Getting Help

Pixeltable Documentation

Pixeltable is a declarative data infrastructure for building multimodal AI applications, enabling incremental storage, transformation, indexing, and orchestration of data.

Introduction

Complete guide to installing and setting up Pixeltable

Installation

Configuration

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.

Quick Start

Use LLMs in your Pixeltable integration workflow

Building with LLMs

Learn the fundamentals of Pixeltable tables, types, and how to build in Pixeltable

Tables

Learn how to create and use virtual derived tables in Pixeltable through views

Views

Learn about iterators for processing documents, videos, audio, and images

Iterators

A comprehensive guide to inserting, referencing, and importing data in Pixeltable

Bringing Data

Learn how to query and transform data in Pixeltable using where() and select()

Building Queries

Computed columns combines automatic calculations with smart incremental updates. Think of them as your data workflow automated.

Computed Columns

Learn how to create, populate and query embedding indexes in Pixeltable

Vector Database

Create and use custom functions (UDFs) in Pixeltable

Custom Functions (UDFs)

Learn Pixeltable core concepts and capabilities through interactive tutorials

Fundamentals

Deep dive into Pixeltable advanced capabilities and patterns

Feature Guides

An Agent Engineering Blueprint powered by Pixeltable

Pixelagent

Extending AI capabilities with Pixeltable MCP servers

Model Context Protocol

Lightweight object detection library built on PyTorch

Pixeltable YOLOX

Explore practical applications and implementation patterns with Pixeltable

Use Cases

Explore Pixeltable capabilities through interactive demos

Interactive Demos

Explore real-world applications built with Pixeltable

Sample Applications

Build a chat application that processes documents, videos, and audio

Multimodal Chatbot

Build a chatbot that remembers conversation history using Pixeltable

Memory

Build AI agents that can invoke custom tools

Tools

Add automated quality assessment to your AI applications using LLM-based evaluation

Evaluations

Build annotation workflows with Pixeltable and Label Studio in two phases

Label Studio

Build image analysis workflows with Pixeltable and Voxel51 in two phases

Voxel51

Use YOLOX object detection in Pixeltable by defining your schema, then using it

YOLOX Object Detection

Build an audio-to-text knowledge base with search capabilities

Audio

Build an image search system using OpenAI Vision and vector embeddings

Image

Build a PDF search system using smart chunking and vector embeddings

Build a web content search system using smart chunking and vector embeddings

Website

Build a multimodal video search workflow with Pixeltable

Video

Explore Pixeltable ecosystem of built-in integrations for AI/ML workflows

Ecosystem

Explore pre-trained models and integrations available in Pixeltable

Model Hub & Repositories

Learn how to integrate custom embedding models with Pixeltable

Embedding Models

Product Updates

Frequently asked questions about Pixeltable

Support

Getting Help

Discord

GitHub

API Reference

Office Hours