haive.agents.reasoning_and_critique.tot.orchestrator
====================================================

.. py:module:: haive.agents.reasoning_and_critique.tot.orchestrator

.. autoapi-nested-parse::

   Tree of Thoughts Orchestrator using MultiAgent.

   This module implements the Tree of Thoughts algorithm using a multi-agent
   approach with MultiAgent coordinating the Candidate Generator
   and Solution Scorer agents.



Classes
-------

.. autoapisummary::

   haive.agents.reasoning_and_critique.tot.orchestrator.TOTResult
   haive.agents.reasoning_and_critique.tot.orchestrator.TreeOfThoughtsOrchestrator


Functions
---------

.. autoapisummary::

   haive.agents.reasoning_and_critique.tot.orchestrator.create_tot_solver


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

.. py:class:: TOTResult(/, **data)

   Bases: :py:obj:`pydantic.BaseModel`


   Result from Tree of Thoughts execution.

   Create a new model by parsing and validating input data from keyword arguments.

   Raises [`ValidationError`][pydantic_core.ValidationError] if the input data cannot be
   validated to form a valid model.

   `self` is explicitly positional-only to allow `self` as a field name.


.. py:class:: TreeOfThoughtsOrchestrator(name = 'tot_orchestrator', engine = None, beam_width = 5, max_iterations = 3, temperature_generate = 0.7, temperature_score = 0.3)

   Orchestrates Tree of Thoughts algorithm using multiple agents.

   Initialize the Tree of Thoughts orchestrator.

   :param name: Name for the orchestrator
   :param engine: LLM configuration for the coordinator
   :param beam_width: Number of top solutions to keep at each iteration
   :param max_iterations: Maximum number of expansion iterations
   :param temperature_generate: Temperature for candidate generation
   :param temperature_score: Temperature for solution scoring


   .. py:method:: solve(problem, initial_seed = None, context = '')
      :async:


      Solve a problem using Tree of Thoughts.

      :param problem: The problem to solve
      :param initial_seed: Optional initial solution seed
      :param context: Additional context or constraints

      :returns: TOTResult with the best solution found



.. py:function:: create_tot_solver(beam_width = 5, max_iterations = 3, **kwargs)
   :async:


   Factory function to create a Tree of Thoughts solver.

   :param beam_width: Number of solutions to keep at each iteration
   :param max_iterations: Maximum iterations to perform
   :param \*\*kwargs: Additional arguments for the orchestrator

   :returns: Configured TreeOfThoughtsOrchestrator instance