Your AI Data Infrastructure

The only Python library that provides incremental storage, transformation, indexing, and orchestration of your multimodal data.

Quick Start☁️ Join Cloud Waitlist
● Apache 2.0 License • Open Source

Build powerful AI applications:

WHY PIXELTABLE?

Multimodal AI Applications

Build multimodal AI apps and agentic workloads with a few lines of code without losing flexibility. Ship to production in days, not months.

INTERACTIVE DEMO

1. Create Multimodal Table

Define a schema for videos and their metadata - the foundation for any AI application.

media_assets• Table
Asset
Category
Metadata
Build with this pattern:
1 / 6
pixeltable_demo.py
Docs
1import pixeltable as pxt
2

3# Create a table for multimodal assets
4media = pxt.create_table("media_assets", {
5    "asset": pxt.Video,
6    "category": pxt.String,
7    "metadata": pxt.Json
8})

A flexible table for any media type - videos, images, audio, documents.

HOW IT WORKS

Declarative. Multimodal. Incremental.

Pixeltable automates storage, orchestration, incremental computation, & model execution. Focus on logic, not infrastructure.

Build
Transform
Retrieve
Serve

1. Unified Data Foundation

Natively manage diverse data types (images, videos, audio, docs, embeddings) without duplication. Persistent, versioned tables. Eliminate separate DBs/stores.

Native Multimodal Types (Image, Video, Audio, Doc, Embeddings, JSON)
No Data Duplication (Local/S3 References)
Persistent & Versioned Tables
Eliminates Separate DBs/Stores
Python
Docs
1import pixeltable as pxt
2

3# Create a directory for your tables
4pxt.create_dir('demo_project')
5

6# Define table with image and text columns
7img_table = pxt.create_table(
8  'demo_project.images', 
9  {
10    'input_img': pxt.Image,
11    'raw_text': pxt.String  # For UDF example in Step 2
12  }
13)
14

15# Insert data (paths or URLs and text)
16img_table.insert([
17  {'input_img': 'image1.jpg', 'raw_text': 'Text for image 1'},
18  {'input_img': 'image2.png', 'raw_text': 'Text for image 2'}
19])
BY THE NUMBERS

Unify Storage and Orchestration

pip install pixeltable→Your entire AI data stack

90%
Before: 1000+After: 100

Reduction in pipeline complexity

Simplify your AI data pipelines with declarative processing

75%
Before: MonthsAfter: Days

Faster development cycles

Accelerate your ML development with automated workflows

60%
Before: $10k/moAfter: $4k/mo

Lower infrastructure costs

Optimize resource usage with intelligent scaling

* Performance metrics based on typical use cases and internal benchmarks.

MULTIMODAL AI DEVELOPMENT

Build Production-Ready AI Applications

Accelerate your multimodal workflows with unified data infrastructure for AI.

Computer Vision

Automate complex CV workflows with unified data management and declarative Python.

frames.add_computed_column(
  objects=yolox(frames.frame)
)
Unified DatasetsDeclarative PythonAutomated PipelinesVersioning

RAG & Semantic Search

Build reliable RAG systems with auto-synced multimodal indexes, simplifying vector DB management.

docs.add_embedding_index(
  'content', embedding=clip
)
Auto-Syncing IndexMultimodal SearchSimplified Vector DBMetadata Filtering

Build AI Agents Faster

Unified infrastructure for agent data, state, and tools. Focus on agent logic, not plumbing.

@pxt.udf
def agent_tool(query: str):
  return process(query)
Unified InfraBuilt-in State/MemoryAny LLM/ToolCustom Python UDFs
View All Examples

A New Kind of Multimodal AI DatabaseStart building with Pixeltable today

Join ML engineers and data scientists using Pixeltable to build powerful multimodal AI applications with unified data management and orchestration.

View on GitHubExplore Documentation