像素表

Publish your own dataset (requires free account)

pxt.publish(source='my-table', destination_uri='pxt://myorg/my-dataset')

Installation

pip install pixeltable

or with uv:

uv add pixeltable

Pixeltable bundles its own transactional database, orchestration engine, and local dashboard. No Docker, no external services — one install is all you need. All data is managed in ~/.pixeltable and accessed through the Python SDK. See Working with External Files and Storage Architecture for details.

Quick Start

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

pip install pixeltable google-genai torch transformers scenedetect

Set your API keys via environment variables or ~/.pixeltable/config.toml. See Configuration for all provider keys and options.

import pixeltable as pxt
from pixeltable.functions import gemini, huggingface

videos = pxt.create_table('video_search', {'video': pxt.Video, 'title': pxt.String})

videos.add_computed_column(scenes=videos.video.scene_detect_adaptive())

videos.add_computed_column(
    response=gemini.generate_content(
        [videos.video, 'Describe this video in detail.'], model='gemini-3-flash-preview'
    )
)

videos.add_computed_column(
    description=videos.response.candidates[0].content.parts[0].text.astype(pxt.String)
)

videos.add_embedding_index('description', embedding=gemini.embed_content.using(model='gemini-embedding-2-preview'))

base_url = 'https://raw.githubusercontent.com/pixeltable/pixeltable/release/docs/resources'
videos.insert([
    {'video': f'{base_url}/bangkok.mp4', 'title': 'Bangkok Street Tour'},
    {'video': f'{base_url}/The-Pursuit-of-Happiness-Video-Extract.mp4', 'title': 'The Pursuit of Happiness'},
])

videos.select(
    videos.title,
    videos.description,
    detections=huggingface.detr_for_object_detection(
        videos.video.extract_frame(timestamp=2.0),
        model_id='facebook/detr-resnet-50',
    ),
).collect()

sim = videos.description.similarity(string='street food')
videos.order_by(sim, asc=False).limit(5).select(videos.title, sim).collect()

Wrap any query as an HTTP endpoint and serve it:

@pxt.query
def search_videos(query_text: str, limit: int = 5):
    sim = videos.description.similarity(string=query_text)
    return videos.order_by(sim, asc=False).limit(limit).select(videos.title, videos.description, sim)

```toml

Tutorials & Cookbooks

Demo

See Pixeltable in action: table creation, computed columns, multimodal processing, and querying in a single workflow.

https://github.com/user-attachments/assets/b50fd6df-5169-4881-9dbe-1b6e5d06cede

Explore: filter, sample, apply UDFs ephemerally

results = ( t.where(t.score > 0.8) .order_by(t.timestamp) .select(t.image, score=t.score) .limit(10) .collect() )

Sample 5 rows and test a UDF (nothing stored, calls parallelized and cached)

t.sample(5).select(t.text, summary=summarize(t.text)).collect()

Or set environment variable: PIXELTABLE_START_DASHBOARD=false

**Highlights:** Table browser with sorting & filtering · Media preview (images, video, audio) · Column lineage visualization · Pipeline graph · Per-column error tracking · CSV export · Auto-refresh

No extra dependencies. No setup. It's just there.
</details>

<details>
<summary><b>Import/Export:</b> I/O & Integration</summary>
<br>

[Import from any source](https://docs.pixeltable.com/howto/cookbooks/data/data-import-csv) and [export to ML formats](https://docs.pixeltable.com/howto/cookbooks/data/data-export-pytorch).

LLM API call

t.add_computed_column( summary=openai.chat_completions( messages=[{'role': 'user', 'content': t.text}], model='gpt-4o-mini' ) )

ML tool integrations

pxt.create_label_studio_project(table, label_config) # Annotation pxt.export_images_as_fo_dataset(table, table.image) # FiftyOne ```

→ Data Import · PyTorch Export · Label Studio · Data Wrangling for ML </details>