Working with Nebius

What it uses

Install

terminal

$pip install pixeltable openai

Environment variables it names

NEBIUS_API_KEY

Pixeltable calls

nebius.chat_completions()nebius.embeddings()pxt.create_table()add_computed_column()insert()add_embedding_index()similarity()

A look at the code

from pixeltable.functions import nebius

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

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

chat_t.add_computed_column(
    output=nebius.chat_completions(
        messages=messages,
        model='Qwen/Qwen3-30B-A3B-Instruct-2507',
        model_kwargs={
            # Optional dict with parameters for the Nebius API
            'max_tokens': 300,
            'temperature': 0.7,
        },
    )
)
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 Ollama in Pixeltable

  Ollama is a popular platform for local serving of LLMs. In this tutorial, we'll show how to integrate Ollama models into a Pixeltable workflow.

  Updated Oct 25, 2026Open in Colab

• Working with OpenAI in Pixeltable

  Pixeltable's OpenAI integration enables you to access OpenAI models via the OpenAI API.

  Updated Oct 29, 2026Open in Colab

• Working with OpenRouter in Pixeltable

  Pixeltable's OpenRouter integration enables you to access multiple LLM providers through a unified API via OpenRouter.

  Updated Oct 19, 2026Open in Colab

• Working with Pydantic in Pixeltable

  Pixeltable's Pydantic integration enables type-safe data insertion using Pydantic models. Instead of inserting raw dictionaries, you can define structured models with validation and insert them directly into Pixeltable tables.

  Updated Aug 14, 2026Open in Colab