.. _auto_ontology_context:

*ONTOLOGY CONTEXT*
==================

Queries a named ARC2 RDF triple-store, introspects its OWL classes, object properties, and datatype properties, and serialises a structured JSON summary for use as context by an LLM agent. Use this worker whenever an AI agent needs schema-level awareness of an ontology graph before formulating SPARQL queries or reasoning over its contents.

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

Tagged: ``arc2``, ``knowledge-graph``, ``llm-context``, ``ontology``, ``owl``, ``rdf``, ``sparql``.

Inputs
------

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

   * - Label
     - ID
     - Type
     - Default
     - Required
     - Description
   * - Ontology Store Name
     - ontology_store_name
     - text
     - —
     - ✓
     - Name of the ARC2 RDF triple-store to analyse (e.g. 'my_model'); the prefix 'arc2_ontology_' is prepended automatically if absent. Required — leave blank only if the store does not yet exist and an empty-context fallback is acceptable.

Outputs
-------

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

   * - Label
     - ID
     - Type
     - Description
   * - Ontology Context
     - context
     - text
     - JSON-encoded ontology summary containing detected ontology type, namespace prefix, node types (OWL classes) with instance counts, edge types (object properties) with source/target class pairs and usage counts, and datatype properties; consumed downstream by LLM or agent workers as structured schema context.

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

- ai_ml.agents
- ai_ml.domain_reasoning
- ai_ml.llm
- platform.ontology

.. raw:: html

   <hr style="margin-top:2em">
   <p style="font-size:11px;color:#888">
   Auto-generated from <code>platform</code> schema. Worker id: <code>ontology_context</code>. Schema hash: <code>0dad039663c6</code>. Hand-curated docs in <code>workerexamples/</code> override this page when present.
   </p>