Working with Microsoft Fabric

What it covers

• Important notes
• Chat Completions with Standard Models
• Chat Completions with Reasoning Models
• Embeddings for Semantic Search
• Combining Chat and Embeddings: RAG Pattern
• Available Models in Fabric
• Key Features

What it uses

Install

terminal

$pip install pixeltable

Pixeltable calls

fabric.chat_completions()fabric.embeddings()pxt.create_table()@pxt.queryadd_computed_column()insert()add_embedding_index()similarity()

A look at the code

# Parse the response to extract just the message content
tickets.add_computed_column(
    response_text=tickets.ai_response.choices[0].message.content
)

One cell of the notebook, copied as it is. The rest is on the docs page.

• Working with Fireworks AI in Pixeltable

  Pixeltable's Fireworks integration enables you to access LLMs hosted on the Fireworks platform.

  Updated Oct 8, 2026Open in Colab

• Working with Gemini in Pixeltable

  Use Google Gemini from Pixeltable with a Google AI Studio API key or Vertex AI: generate content, images with Nano Banana and Imagen, and video with Veo.

  Updated Oct 23, 2026Open in Colab

• Working with Groq in Pixeltable

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

  Updated Aug 19, 2026Open in Colab

• Working with Hugging Face

  Pixeltable provides seamless integration with Hugging Face datasets and models.

  Updated Feb 3, 2026Open in Colab