.. _auto_text_similarity:

*TEXT SIMILARITY*
=================

Computes a similarity score between two text strings, quantifying how closely a candidate text matches a reference base text. Use this worker when you need to compare labels, descriptions, or any free-text fields for fuzzy or exact likeness within a workflow.

When to use
-----------

Classification: **process**.

Tagged: ``fuzzy_match``, ``nlp``, ``string_comparison``, ``text_processing``, ``text_similarity``.

Inputs
------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20 20 20

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Base Text
     - base_text
     - text
     - —
     - 
     - The reference text string against which the comparison is made; provide the canonical or ground-truth phrase/sentence to use as the similarity baseline.
   * - Compare Text
     - compare_text
     - text
     - —
     - 
     - The candidate text string to compare against the base text; each repeating instance is evaluated independently on the same line, producing one similarity result per pair.

Outputs
-------

.. list-table::
   :header-rows: 1
   :widths: 20 20 20 20

   * - Label
     - ID
     - Type
     - Description
   * - text_similarity_output_1
     - text_similarity_output_1
     - text
     - Numeric similarity score (typically 0.0–1.0, where 1.0 indicates identical texts) or a structured representation of the comparison result between the base and compare text inputs.

Disciplines
-----------

- ai_ml.llm
- data.statistics

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>transformation</code> schema. Worker id: <code>text_similarity</code>. Schema hash: <code>81af74913294</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>