Power AI App BackendsWithout Data Plumbing

Unified Storage, Orchestration, and Retrieval for Multimodal AI Workloads

Start Building in 2 Minutes

85% lessdata pipeline code—

Shipped in 3 days(not 3 weeks)—

Open Source • From the creator of Apache Parquet and Impala and engineers who worked at:

1# Replace complex pipelines with simple declarations
2import pixeltable as pxt
3from pixeltable.functions import openai, yolox
4from pixeltable.iterators import FrameIterator
5
6# Create table - no infrastructure code needed
7videos = pxt.create_table('content', {
8    'video': pxt.Video,
9    'title': pxt.String
10})
11
12# Automatic frame extraction
13frames = pxt.create_view('frames', videos,
14    iterator=FrameIterator.create(video=videos.video, fps=1)
15)
16
17# Define what you want computed - runs automatically
18frames.add_computed_column(
19    objects=yolox(frames.frame, model_id='yolox_s')
20)
21frames.add_computed_column(
22    description=openai.vision(
23        frames.frame,
24        prompt="Describe what's happening in this frame",
25        model='gpt-4o-mini'
26    )
27)
28
29# Pixeltable handles orchestration, caching, incremental updates

1. INGEST

pxt.Video

↓

2. TRANSFORM

frames

↓

3. AI COMPUTE

detect

describe

Power AI App Backends
Without Data Plumbing

Storage

Unified

Compute

Auto

Native

Pipeline Code

-85%

Time to Ship

3 days

Your AI Data Stack

pip install pixeltable

Reduction in pipeline complexity

Simplify your AI data pipelines with declarative processing

90%

+90% gain

Faster development cycles

Accelerate your ML development with automated workflows

75%

+75% gain

Lower infrastructure costs

Deploy serverless functions when you need them, all without leaving pixeltable

60%

+60% gain

Quick Start GitHub

What Pixeltable Replaces

One declarative system instead of 10+ tools

Database

PostgreSQL + MongoDB

Pixeltable Tables

4 systems → 1

Workflow

Airflow + Celery + cron

Auto-Orchestration

3 tools → 0

Vector DB

Pinecone + Weaviate

Native Vector Search

2 DBs → 0

Transform

Custom ETL Pipelines

Computed Columns

1000 LOC → 10

Cache

Redis + S3 Caching

Incremental Compute

Auto-managed

Versioning

Manual Version Control

Built-in Lineage

Automatic

Total Infrastructure Savings~90%

See Complete Architecture

Top Features

View All

Video Intelligence

Frame extraction & analysis

10x Faster

+847%vs manual pipelines

frames.add_computed_column(objects=yolox(frames.frame))

RAG & Search

Auto-synced vector indexes

5x Simpler

+422%dev velocity

docs.add_embedding_index("content", embedding=clip)

AI Agents

Unified state & memory

90% Less Code

+1156%productivity

@pxt.udf
def agent_tool(query: str):
  return process(query)

Live Projects

3 Active

Code Examples

t.add_computed_column(
  objects=yolox(...)
)

docs.add_embedding_index(
  'content', ...
)

@pxt.udf
def agent_tool(...):
  ...

How Pixeltable Works

3 steps to production AI apps

Create Your Data

Define tables with native multimodal types

< 1 min

pxt.create_table('videos', {'video': pxt.Video})

Transform

Add computed columns with AI models

< 1 min

t.add_computed_column(objects=yolox(...))

Query & Deploy

SQL-like queries, auto-orchestration

< 1 min

results = t.where(t.score > 0.8).select(...)

Get Started Now

Performance

Lines of Code-90%

Before: 1000+

After: 100

Dev Time-75%

Before: Months

After: Days

Infra Cost-60%

Before: $10k/mo

After: $4k/mo

Database, Orchestration, and AI
Forged into One Data Infrastructure

Pixeltable replaces the complex multi-system architecture needed for AI applications (databases, file storage, vector DBs, APIs, orchestration) with a single declarative table interface that natively handles multimodal data like images, videos, and documents.

Loading architecture diagram...

The Anatomy of a Multimodal AI Agent

Explore the code behind Pixelbot, built on Pixeltable. See how declarative data infrastructure simplifies workflows like RAG, tool use, and multimodal data handling.

Multimodal AI Agent/

Try Live Now View Code

pixelbot

setup_pixeltable.py

Storage & Orchestration

endpoint.py

Web Server & API Endpoints

functions.py

UDFs and tool definitions

config.py

Model settings and configuration

requirements.txt

Dependencies

.env

Environment variables

Standard web app files (not Pixeltable-specific)

data

static

templates

logs

6 Core Files

Lineage, Versioning, Caching

Built-in

setup_pixeltable.py

GitHub Project

1pxt.create_dir("agents", if_exists="ignore")
2
3# === DOCUMENT PROCESSING ===
4documents = pxt.create_table(
5    "agents.collection",
6    {
7        "document": pxt.Document, 
8        "uuid": pxt.String, 
9        "timestamp": pxt.Timestamp, 
10        "user_id": pxt.String
11    },
12)
13chunks = pxt.create_view(
14    "agents.chunks",
15    documents,
16    iterator=DocumentSplitter.create(
17        document=documents.document,
18        separators="paragraph",
19        metadata="title, heading, page"
20    ),
21)
22chunks.add_embedding_index(
23    "text",
24    string_embed=sentence_transformer.using(
25        model_id=config.EMBEDDING_MODEL_ID
26    ),
27)
28
29@pxt.query
30def search_documents(query_text: str, user_id: str):
31    sim = chunks.text.similarity(query_text)
32    return (
33        chunks
34        .where((chunks.user_id == user_id) & (sim > 0.5))
35        .order_by(sim, asc=False)
36        .select(
37            chunks.text, 
38            source_doc=chunks.document, 
39            sim=sim
40        )
41        .limit(20)
42    )
43
44# === IMAGE PROCESSING ===
45images = pxt.create_table(
46    "agents.images",
47    {
48        "image": pxt.Image, 
49        "uuid": pxt.String, 
50        "timestamp": pxt.Timestamp, 
51        "user_id": pxt.String
52    },
53)
54images.add_computed_column(
55    thumbnail=pxt_image.b64_encode(
56        pxt_image.resize(images.image, size=(96, 96))
57    ),
58)
59images.add_embedding_index(
60    "image",
61    embedding=clip.using(model_id=config.CLIP_MODEL_ID),
62)
63
64# ... and so on for Video, Audio, Memory, Chat History, Personas, Image Generation ...
65
66# === AGENT WORKFLOW DEFINITION ===
67tools = pxt.tools(
68    functions.get_latest_news,
69    functions.fetch_financial_data,
70    search_video_transcripts,
71)
72
73tool_agent = pxt.create_table(
74    "agents.tools",
75    {
76        "prompt": pxt.String,
77        "timestamp": pxt.Timestamp,
78        "user_id": pxt.String,
79        "initial_system_prompt": pxt.String,
80        "final_system_prompt": pxt.String,
81        "max_tokens": pxt.Int,
82        "temperature": pxt.Float,
83    },
84)
85
86# === DECLARATIVE WORKFLOW WITH COMPUTED COLUMNS ===
87# Step 1: Initial LLM Reasoning (Tool Selection)
88tool_agent.add_computed_column(
89    initial_response=messages(
90        model=config.CLAUDE_MODEL_ID,
91        system=tool_agent.initial_system_prompt,
92        messages=[{"role": "user", "content": tool_agent.prompt}],
93        tools=tools,
94        tool_choice=tools.choice(required=True),
95    ),
96)
97
98# Step 2: Tool Execution
99tool_agent.add_computed_column(
100    tool_output=invoke_tools(tools, tool_agent.initial_response)
101)
102
103# Step 3: Context Retrieval (Parallel RAG)
104tool_agent.add_computed_column(
105    doc_context=search_documents(tool_agent.prompt, tool_agent.user_id)
106)
107# ... other context retrieval steps ...
108
109# Step 7: Final LLM Reasoning (Answer Generation)
110tool_agent.add_computed_column(
111    final_response=messages(
112        model=config.CLAUDE_MODEL_ID,
113        system=tool_agent.final_system_prompt,
114        messages=tool_agent.final_prompt_messages,
115    ),
116)
117
118# Step 8: Extract Final Answer Text
119tool_agent.add_computed_column(
120    answer=tool_agent.final_response.content[0].text
121)

How Pixeltable Works

Store multimodal data in tables, define transformations as computed columns, and query everything together. Pixeltable handles all the orchestration, caching, and model execution automatically.

Build

Transform

Retrieve

Serve

1. Connect to Your Data

Connect directly to your existing object stores (S3, local) without moving or duplicating data. Pixeltable organizes your files into queryable, versioned tables, eliminating the need for separate databases or vector stores.

Connect to Your Data In-Place (S3 & Local)

Zero-Duplication Design (References your files)

Persistent & Versioned Tables

Native Multimodal Types (Video, Image, Audio, etc.)

Try in Playground View Docs

pixeltable_workflow.py

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
12    }
13)
14
15# Insert data (paths or URLs and text)
16img_table.insert([
17    {
18        'input_img': 'image1.jpg', 
19        'raw_text': 'Text for image 1'
20    },
21    {
22        'input_img': 'image2.png', 
23        'raw_text': 'Text for image 2'
24    }
25])

Your Backend for Multimodal AI Applications

pip install pixeltable→Your entire AI data stack

90%

Reduction in pipeline complexity

Simplify your AI data pipelines with declarative processing

75%

Faster development cycles

Accelerate your ML development with automated workflows

60%

Lower infrastructure costs

Deploy serverless functions when you need them, all without leaving pixeltable

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

See Detailed Workflows

Everything You Need to Know

Common questions about building with Pixeltable

Declarative Data Infrastructure
for Multimodal AI

Go from AI experiment to production pipeline in seconds, not months.

Start Building with Pixeltable 10-Min Quickstart

Power AI App BackendsWithout Data Plumbing

Power AI App Backends
Without Data Plumbing

Your AI Data Stack

What Pixeltable Replaces

Top Features

Live Projects

Code Examples

How Pixeltable Works

Performance

Database, Orchestration, and AI
Forged into One Data Infrastructure

The Anatomy of a Multimodal AI Agent

How Pixeltable Works

1. Connect to Your Data

Your Backend for Multimodal AI Applications

Reduction in pipeline complexity

Faster development cycles

Lower infrastructure costs

Build Production-Ready AI Applications

Computer Vision

RAG & Semantic Search

Build AI Agents Faster

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?

Declarative Data Infrastructure
for Multimodal AI

Power AI App BackendsWithout Data Plumbing

Power AI App BackendsWithout Data Plumbing

Your AI Data Stack

What Pixeltable Replaces

Top Features

Live Projects

Code Examples

How Pixeltable Works

Performance

Database, Orchestration, and AIForged into One Data Infrastructure

The Anatomy of a Multimodal AI Agent

How Pixeltable Works

1. Connect to Your Data

Your Backend for Multimodal AI Applications

Reduction in pipeline complexity

Faster development cycles

Lower infrastructure costs

Build Production-Ready AI Applications

Computer Vision

RAG & Semantic Search

Build AI Agents Faster

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?

Declarative Data Infrastructurefor Multimodal AI

Power AI App Backends
Without Data Plumbing

Database, Orchestration, and AI
Forged into One Data Infrastructure

Declarative Data Infrastructure
for Multimodal AI