How does embedding index work?

You name the column and the embedding function. New and changed rows are embedded. Unchanged rows stay as they are. A similarity query orders rows by distance to the question.

Retrieval

What is an embedding index?

An embedding index ranks nearest neighbors for a query and stays attached to the table that owns those rows.

Updated 2026-09-29 · Part of What is an embedding?

How it works

You name the column and the embedding function.
New and changed rows are embedded. Unchanged rows stay as they are.
A similarity query orders rows by distance to the question.

What it is not

It is not a standalone vector database you load and sync yourself.

embedding index: this, and the thing it is confused with

embedding index: this, and the thing it is confused with
	This	Not this
Lives on	The table that holds the pieces	A second database you copy into
When rows change	Those rows are re-embedded	A sync job you operate
Query	Nearest rows of that table	Nearest vectors with no source row

Where Pixeltable fits

Pixeltable declares it as __indexes__ = [pxt.EmbeddingIndex(...)] on the class. Insert updates the index for that row.

import pixeltable as pxt
from pixeltable.functions.huggingface import sentence_transformer

TableModel = pxt.model_base()
text_embed = sentence_transformer.using(model_id='all-MiniLM-L6-v2')

class Passages(TableModel, name='passages'):
    text: pxt.String

    __indexes__ = [
        pxt.EmbeddingIndex(text, string_embed=text_embed),
    ]

Questions

How does embedding index work?: You name the column and the embedding function. New and changed rows are embedded. Unchanged rows stay as they are. A similarity query orders rows by distance to the question.
What is embedding index often confused with?: It is not a standalone vector database you load and sync yourself.