Working with Hugging Face

What it covers

• Importing datasets directly into Pixeltable tables
• Working with dataset splits (train/test/validation)
• Streaming large datasets with IterableDataset
• Type mappings from Hugging Face to Pixeltable
• Using Hugging Face models for embeddings

What it uses

Install

terminal

$pip install pixeltable datasets torch transformers sentence-transformers

Pixeltable calls

pxt.create_table()group_by()insert()add_embedding_index()similarity()

A look at the code

from pixeltable.functions.huggingface import clip

# Add CLIP embedding index for cross-modal image search
images.add_embedding_index(
    'Image', embedding=clip.using(model_id='openai/clip-vit-base-patch32')
)

# Search images using text
sim = images.Image.similarity(string='anime character with red clothes')
images.order_by(sim, asc=False).limit(3).select(
    images.Image, images.Name, sim=sim
).collect()

One cell of the notebook, copied as it is. Open it in Colab for the rest.

• Working with Jina AI in Pixeltable

  Pixeltable's Jina AI integration enables you to access state-of-the-art embedding and reranker models via the Jina AI API.

  Updated Apr 10, 2026Open in Colab

• Working with llama.cpp in Pixeltable

  This tutorial demonstrates how to use Pixeltable's built-in llama.cpp integration to run local LLMs efficiently.

  Updated Oct 25, 2026Open in Colab

• Working with Mistral AI in Pixeltable

  Pixeltable's Mistral AI integration enables you to access Mistral's LLM and other models via the Mistral AI API.

  Updated Aug 3, 2026Open in Colab

• Working with Nebius

  Pixeltable's Nebius Token Factory integration enables you to access Nebius language and embedding models via an OpenAI-compatible API.

  Updated Aug 22, 2026Open in Colab