Ingest a web page

What it covers

• Insert the URL
• Chunk it, two ways
• Make it searchable

What it uses

Pixeltable calls

document.document_splitter()pxt.create_table()pxt.create_view()insert()add_embedding_index()similarity()

A look at the code

from pixeltable.functions.huggingface import sentence_transformer

embed = sentence_transformer.using(model_id='intfloat/e5-large-v2')
by_paragraph.add_embedding_index('text', string_embed=embed)

sim = by_paragraph.text.similarity(string='how do ants communicate')
by_paragraph.order_by(sim, asc=False).limit(5).select(by_paragraph.text, sim).collect()

One block of the recipe, copied as it is. The rest is on the docs page.

• 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

• Translate text between languages

  Automatically translate content into multiple languages using LLMs.

  Updated Apr 10, 2026Open in Colab