pipeworks_mud_mapper.services.ollama_client
===========================================

.. py:module:: pipeworks_mud_mapper.services.ollama_client

.. autoapi-nested-parse::

   Thin client for interacting with a local Ollama server.

   This module isolates HTTP communication so callbacks can remain focused
   on UI state and response handling. It also provides a central place for
   timeouts and request formatting.



Functions
---------

.. autoapisummary::

   pipeworks_mud_mapper.services.ollama_client.list_models
   pipeworks_mud_mapper.services.ollama_client.chat


Module Contents
---------------

.. py:function:: list_models(server_url)

   Return the list of models from the Ollama server.

   :param server_url: Base URL for the Ollama server (e.g., http://localhost:11434).
   :type server_url: :py:class:`str`

   :returns: Raw model entries from the Ollama /api/tags endpoint.
   :rtype: :py:class:`list[dict[str`, :py:class:`Any]]`


.. py:function:: chat(server_url, model, messages, options)

   Send a chat request to the Ollama /api/chat endpoint.

   :param server_url: Base URL for the Ollama server (e.g., http://localhost:11434).
   :type server_url: :py:class:`str`
   :param model: Ollama model identifier (e.g., "llama3:8b").
   :type model: :py:class:`str`
   :param messages: Chat message objects with role/content keys.
   :type messages: :py:class:`list[dict[str`, :py:class:`str]]`
   :param options: Ollama generation options (seed, temperature, etc.).
   :type options: :py:class:`dict[str`, :py:class:`Any]`

   :returns: Parsed JSON response from the Ollama server.
   :rtype: :py:class:`dict[str`, :py:class:`Any]`