> ## Documentation Index
> Fetch the complete documentation index at: https://docs.parable.work/llms.txt
> Use this file to discover all available pages before exploring further.

# Plot Plugin Primer

> Extend Plot SQL with reusable first-party and custom computations.

Plot Plugins make specialized computations available inside Plot SQL. A Plot
owns the query and its resulting table; a Plot Plugin owns a reusable operation
that the query can invoke.

The first-party Plot Plugins cover the two model-backed operations available
today:

<Columns cols={2}>
  <Card title="Ponder" icon="brain" href="/plugins/plot-plugins/ponder">
    Classify, extract, and generate typed values with one model call per input
    row.
  </Card>

  <Card title="Embed" icon="vector-square" href="/plugins/plot-plugins/embed">
    Turn text into comparable vectors for retrieval and similarity workflows.
  </Card>
</Columns>

## How Plot Plugins fit

1. A Plot selects and shapes Workspace data with SQL.
2. A Plot Plugin evaluates its operation for the rows that reach the function.
3. DataFusion returns Arrow values as part of the query result.
4. A materialized Plot publishes that result in the
   [Parable Pool](/protocols/sql/data-catalog/parable-pool).

Run the SQL through an SDK for the ordinary path, or use Flight SQL when you are
building a protocol-level client. See [Query with the SDKs](/protocols/sql/query-with-sdks)
and [Flight SQL](/protocols/sql/flight-sql).

<Note>
  A [Plot](/ponder/parables/pieces/plots) is a Piece with its own query and
  result. A Plot Plugin is a function that a Plot can call; it is not another
  Piece.
</Note>

Internal authors can implement another operation from the
[Custom Plot Plugins](/plugins/plot-plugins/custom-plugins) reference.