Working with Together AI in Pixeltable

What it uses

Install

terminal

$pip install pixeltable together

Environment variables it names

TOGETHER_API_KEY

Pixeltable calls

together.chat_completions()together.image_generations()pxt.create_table()add_computed_column()insert()

A look at the code

from pixeltable.functions import together

chat_t = pxt.create_table('together_demo/chat', {'input': pxt.String})

messages = [{'role': 'user', 'content': chat_t.input}]

chat_t.add_computed_column(
    output=together.chat_completions(
        messages=messages,
        model='Qwen/Qwen3.5-9B',
        model_kwargs={
            # Optional dict with parameters for the Together API
            'max_tokens': 300,
            'stop': ['\n'],
            'temperature': 0.7,
            'top_p': 0.9,
        },
    )
)
chat_t.add_computed_column(
    response=chat_t.output.choices[0].message.content
)

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

• Working with Twelve Labs in Pixeltable

  Twelve Labs provides multimodal embeddings that project text, images, audio, and video into the same semantic space. This enables true cross-modal search - the most powerful feature of this integration.

  Updated Feb 12, 2026Open in Colab

• Working with vLLM

  This tutorial demonstrates how to use Pixeltable's built-in vLLM integration to run local LLMs with high-throughput inference.

  Updated Jun 12, 2026Open in Colab

• Working with Voyage AI in Pixeltable

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

  Updated Aug 3, 2026Open in Colab

• Working with Voxel51 for Visualization in Pixeltable

  Pixeltable can export data directly from tables and views to the popular Voxel51 frontend, providing a way to visualize and explore image and video datasets.

  Updated Apr 11, 2026Open in Colab