Video Intelligence Pipeline in 20 MinutesIterate on your data, not your infrastructure

Multimodal DataMade Simple

Every team building with video, audio, images, and documents stitches together 5–8 services. The real cost isn't the wiring — it's the lost feedback loop. Pixeltable ends that.

AI Data Infrastructure

Declarative

Storage Orchestration Retrieval

Incremental

From the creators of Apache Parquet and Impala and engineers who worked at:

Your data is scattered.

Ingest

You need to know where your data is, where it came from, and where it goes — as you build and as you grow. That requires integrity, not more glue.

What you get

The only system where video, audio, images, and documents are first-class column types — not opaque blobs. Schema, versioning, and lineage from the moment data enters. Your files stay where they are.

Replaces

boto3 upload scriptsMetadata DBSync glue code

Learn more

Tables & Data Type System Cloud Storage

1media = pxt.create_table('app.media', {
2  'video': pxt.Video,
3  'doc': pxt.Document,
4  'meta': pxt.Json
5})
6
7media.insert([
8  {'video': 's3://bucket/demo.mp4'},
9  {'doc': '/local/report.pdf'}
10])

Insert a row → every downstream step triggers automatically. One system of record for all modalities.

Your time is wasted.

Process

On ETL, caching, retries, type safety — not on the AI logic that matters. Pixeltable handles the plumbing so you can focus on what you're building.

Your infrastructure doesn't compound.

Ship

Shipping is easy. Evolving is hard. Every iteration should make your system smarter — that's the competitive advantage glue code can never provide.

Get Started Contact Us GitHub

Free & open source · Apache 2.0 · No account required

See It In Action

Define your entire data processing and AI workflow declaratively using computed columns on tables. Focus on your application logic, not the data plumbing.

Colab GitHub Starter Kit

▶ Demo

Transactional, incremental, fully versioned — multimodal AI workloads that run themselves

1# Video intelligence — ingest, extract, enrich, index, query
2import pixeltable as pxt
3from pixeltable.iterators import FrameIterator
4from pixeltable.functions import yolox, gemini, whisper, twelvelabs
5from pixeltable.functions.huggingface import clip, sentence_transformer
6
7# 01 Ingest — native multimodal types
8videos = pxt.create_table('app.videos', {
9    'video': pxt.Video,
10    'title': pxt.String,
11})
12
13# 02 Extract — frames, audio, transcript (automatic on insert)
14frames = pxt.create_view('app.frames', videos,
15    iterator=FrameIterator.create(video=videos.video, fps=1)
16)
17videos.add_computed_column(audio=videos.video.extract_audio())
18videos.add_computed_column(
19    transcript=whisper.transcribe(videos.audio, model='base')
20)
21
22# 03 Enrich — Gemini multimodal + YOLOX + custom UDF
23@pxt.udf
24def label_scene(detections: list[dict], description: str) -> str:
25    objects = [d['class'] for d in detections[:5]]
26    return f"{description} | objects: {', '.join(objects)}"
27
28videos.add_computed_column(
29    description=gemini.generate_content(
30        [videos.video, 'Describe this video in one sentence.'],
31        model='gemini-2.5-flash'
32    )
33)
34frames.add_computed_column(
35    detections=yolox(frames.frame, model_id='yolox_s')
36)
37frames.add_computed_column(
38    label=label_scene(frames.detections, videos.description)
39)
40
41# 04 Index — CLIP, MiniLM, Twelve Labs — always in sync
42frames.add_embedding_index('frame',
43    image_embed=clip.using(model_id='openai/clip-vit-base-patch32'))
44frames.add_embedding_index('label',
45    string_embed=sentence_transformer.using(model_id='all-MiniLM-L6-v2'))
46videos.add_embedding_index('video',
47    embedding=twelvelabs.embed.using(model_name='marengo3.0'))
48
49# 05 Query — similarity + metadata filtering in one expression
50@pxt.query
51def find_scenes(query_text: str, ref_image: pxt.Image, title: str):
52    text_sim = frames.label.similarity(query_text)
53    img_sim = frames.frame.similarity(ref_image)
54    return (frames
55        .where(videos.title.contains(title))
56        .order_by(text_sim + img_sim, asc=False)
57        .limit(10)
58        .select(frames.frame, frames.label)
59    )

app.videostable

Column	Type	Computed With
video	Video
title	String
audio	Audio	extract_audio()
transcript	Json	whisper(base)
description	String	gemini(video)
embedding_index		Twelve Labs (video)

app.framesview → videos

Column	Type	Computed With
frame	Image	FrameIterator
detections	Json	yolox(frame)
label	String	@pxt.udf
embedding_index		CLIP (image)
embedding_index		MiniLM (text)

FastAPIserve

POST/api/videos→ insert

GET/api/search→ find_scenes()

GET/api/frames→ .select().collect()

Insert a video → Gemini, YOLOX, Whisper + custom @pxt.udf as computed columns → CLIP, MiniLM, Twelve Labs indexes → query via @pxt.query. Experiment to production.

From Raw Data to Production

Deploy as a full backend or a sidecar to your existing stack.

Loading architecture diagram...

Watch & Learn

Tutorials, conference talks, and deep-dives from the Pixeltable team.

10 min

DB School Podcast

Developing with AI Tools

Pixeltable's declarative API means AI coding assistants get it right on the first try. Ten lines of code gives you a persistent, versioned, incrementally-optimized pipeline.

Building with LLMs Why vibe-coded apps break

llms.txt

Concise documentation for LLMs

llms-full.txt

Complete API reference for LLMs

MCP Server

Interactive Pixeltable exploration — tables, queries, Python REPL

Claude Code Skill

Deep Pixeltable expertise for Claude

AGENTS.md

Architecture guide for AI agents working with your codebase

Your Backend for Multimodal AI

pip install pixeltableYour entire AI data stack

Instead of ...	Pixeltable gives you ...
PostgreSQL / MySQL	`pxt.create_table()`— schema is Python, versioned automatically
Pinecone / Weaviate / Qdrant	`add_embedding_index()`— one line, stays in sync
S3 / boto3 / blob storage	`pxt.Image / Video / Audio / Document`— native types with caching
Airflow / Prefect / Celery	`Computed columns`— trigger on insert — no orchestrator needed
LangChain / LlamaIndex (RAG)	`@pxt.query + .similarity()`— computed column chaining
pandas / polars (multimodal)	`.sample(), add_computed_column()`— prototype to production
DVC / MLflow / W&B	`history(), revert(), time travel`— built-in snapshots
Custom retry / rate-limit / caching	`Built into every AI integration`— results cached, only new rows recomputed

Use Cases

What Can You Build?

Three paths from day one — all built on the same table abstraction, same pip install

Data Wrangling for ML

Curate, augment, and export training datasets. Auto-annotate with AI, version everything, export to Parquet or PyTorch.

frames = pxt.create_view('ml.frames', videos,
  iterator=FrameIterator.create(video=v.video, fps=1))
frames.add_computed_column(detections=yolox(frames.frame))
export_parquet(frames, 'training_data/')

Multimodal IngestAuto-Annotate with AIVersion & SnapshotExport Parquet / Pandas

Learn more

Agents & MCP

Tool calling, persistent memory, and decision traces — not stateless glue. UDFs as LLM tools, MCP servers, semantic recall.

tools = pxt.tools(get_weather, search_docs)
agent.add_computed_column(response=chat_completions(
  messages=msgs, tools=tools))
memory.add_embedding_index('content', string_embed=embed_fn)

@pxt.udf as ToolsMCP Server IntegrationPersistent MemorySemantic Recall

Learn more

End-to-End Multimodal

Video in, finished product out. RAG, semantic search, multimodal APIs — one table, same primitives.

videos.add_computed_column(transcript=whisper.transcribe(audio))
videos.add_computed_column(hook_video=gemini.generate_videos(...))
videos.add_computed_column(final=with_audio(hook_video, tts_audio),
  destination='s3://bucket/output/')

Video / Audio / Image / TextWhisper + Gemini + VeoAuto-assemble PipelineS3 / Cloud Delivery

Learn more

Get Started in 5 Minutes Explore Public Datasets

Everything You Need to Know

Common questions about building with Pixeltable

Every Era of DataGets an Owner

Oracle for relational. Snowflake for analytics. Databricks for batch.
The multimodal data plane is next.

Start Building with Pixeltable 10-Min Quickstart

Multimodal DataMade Simple

Your data is scattered.

Your time is wasted.

Your infrastructure doesn't compound.

See It In Action

From Raw Data to Production

Watch & Learn

Image Editing with Rev

Pixeltable Overview

Data Council Talk

DB School Podcast

Developing with AI Tools

Your Backend for Multimodal AI

What Can You Build?

Data Wrangling for ML

Agents & MCP

End-to-End Multimodal

Everything You Need to Know

What is Pixeltable?

Why use Pixeltable?

How does Pixeltable work?

What AI models can I use with Pixeltable?

What types of data can Pixeltable handle?

Where do I put my data?

Every Era of DataGets an Owner