haive.agents.rag.query_decomposition.agent
==========================================

.. py:module:: haive.agents.rag.query_decomposition.agent

.. autoapi-nested-parse::

   Query Decomposition Agents.

   Modular agents for breaking down complex queries into manageable sub-queries.
   Can be plugged into any workflow with compatible I/O schemas.



Classes
-------

.. autoapisummary::

   haive.agents.rag.query_decomposition.agent.AdaptiveQueryDecomposerAgent
   haive.agents.rag.query_decomposition.agent.ContextualDecomposition
   haive.agents.rag.query_decomposition.agent.ContextualQueryDecomposerAgent
   haive.agents.rag.query_decomposition.agent.HierarchicalDecomposition
   haive.agents.rag.query_decomposition.agent.HierarchicalQueryDecomposerAgent
   haive.agents.rag.query_decomposition.agent.QueryDecomposerAgent
   haive.agents.rag.query_decomposition.agent.QueryDecomposition
   haive.agents.rag.query_decomposition.agent.QueryType
   haive.agents.rag.query_decomposition.agent.SubQuery


Functions
---------

.. autoapisummary::

   haive.agents.rag.query_decomposition.agent.create_query_decomposer
   haive.agents.rag.query_decomposition.agent.get_query_decomposer_io_schema


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

.. py:class:: AdaptiveQueryDecomposerAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Adaptive query decomposition that selects best strategy.


   .. py:method:: build_graph()

      Build adaptive decomposition graph.



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

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


   Context-aware query decomposition.

   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:: ContextualQueryDecomposerAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Context-aware query decomposition agent.


   .. py:method:: build_graph()

      Build contextual decomposition graph.



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

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


   Hierarchical query decomposition with levels.

   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:: HierarchicalQueryDecomposerAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Hierarchical query decomposition agent.


   .. py:method:: build_graph()

      Build hierarchical decomposition graph.



.. py:class:: QueryDecomposerAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Basic query decomposition agent.


   .. py:method:: build_graph()

      Build query decomposition graph.



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

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


   Complete query decomposition result.

   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:: QueryType

   Bases: :py:obj:`str`, :py:obj:`enum.Enum`


   Types of queries for decomposition strategy.

   Initialize self.  See help(type(self)) for accurate signature.


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

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


   Individual sub-query in decomposition.

   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:function:: create_query_decomposer(decomposer_type = 'basic', llm_config = None, **kwargs)

   Create a query decomposer agent.

   :param decomposer_type: Type of decomposer to create
   :param llm_config: LLM configuration
   :param \*\*kwargs: Additional arguments

   :returns: Configured query decomposer agent


.. py:function:: get_query_decomposer_io_schema()

   Get I/O schema for query decomposers for compatibility checking.