Use a table pipeline as a reusable function

How it works

What it covers

• Create an "agent" table with computed columns
• Convert the table to a callable UDF with pxt.udf(table, return_value=...)
• Use the table UDF in other tables' computed columns

What it uses

Install

terminal

$pip install pixeltable openai

Environment variables it names

OPENAI_API_KEY

Pixeltable calls

openai.chat_completions()pxt.create_table()pxt.udf()add_computed_column()insert()

A look at the code

# Add the LLM call as a computed column
summarizer.add_computed_column(
    response=chat_completions(
        messages=[
            {
                'role': 'user',
                'content': 'Summarize this in one sentence:\n\n'
                + summarizer.text,
            }
        ],
        model='gpt-4o-mini',
    )
)

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

• Look up structured data with retrieval UDFs

  Create lookup functions that query tables by key—for customer records, product catalogs, or financial data.

  Updated Oct 27, 2026Open in Colab

• Use tool calling and MCP servers with LLMs

  Enable LLMs to call functions and tools, then execute the results automatically.

  Updated Oct 16, 2026Open in Colab

• Agentic Patterns

  Build the six architectural patterns of agentic AI (prompt chaining, routing, parallelization, tool use, evaluator-optimizer, orchestrator-worker) and the ReAct and planning strategies as Pixeltable tables and computed columns.

  Updated Sep 3, 2026Open in Colab

• Build a RAG pipeline

  Create a retrieval-augmented generation system that answers questions using your documents as context.

  Updated Apr 10, 2026Open in Colab