Extract named entities from text

How it works

What it covers

• Extract entities as structured JSON
• Use OpenAI's structured output for reliable parsing
• Access extracted entities as queryable 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()add_computed_column()insert()

A look at the code

# Add entity extraction column
extraction_prompt = (
    'Extract all named entities from the following text:\n\n'
    + articles.content
)

articles.add_computed_column(
    extraction_response=chat_completions(
        messages=[{'role': 'user', 'content': extraction_prompt}],
        model='gpt-4o-mini',
        model_kwargs={'response_format': entity_schema},
    )
)

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

• Ingest a web page

  Insert a URL as a document, then compare chunking strategies on it

  Recipe · Updated Sep 21, 2026

• Split documents into chunks for RAG

  Break PDFs and documents into searchable chunks for retrieval-augmented generation (RAG) pipelines.

  Updated Apr 10, 2026Open in Colab

• Extract text from PowerPoint, Word, and Excel files

  Transform office documents into searchable, analyzable text data.

  Updated Apr 10, 2026Open in Colab

• Summarize text with LLMs

  Generate concise summaries of long text, articles, or documents using large language models.

  Updated Sep 3, 2026Open in Colab