haive.agents.rag.self_route.agent
=================================

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

.. autoapi-nested-parse::

   Self-Route RAG Agents.

   from typing import Any
   Implementation of self-routing RAG with dynamic strategy selection and iterative planning.
   Uses structured output models for complex routing decisions and preprocessing.



Classes
-------

.. autoapisummary::

   haive.agents.rag.self_route.agent.IterativePlan
   haive.agents.rag.self_route.agent.IterativePlannerAgent
   haive.agents.rag.self_route.agent.QueryAnalysis
   haive.agents.rag.self_route.agent.QueryAnalyzerAgent
   haive.agents.rag.self_route.agent.QueryComplexity
   haive.agents.rag.self_route.agent.RoutingDecision
   haive.agents.rag.self_route.agent.RoutingDecisionAgent
   haive.agents.rag.self_route.agent.RoutingStrategy
   haive.agents.rag.self_route.agent.SelfRouteRAGAgent


Functions
---------

.. autoapisummary::

   haive.agents.rag.self_route.agent.create_self_route_rag_agent
   haive.agents.rag.self_route.agent.get_self_route_rag_io_schema


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

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

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


   Iterative processing plan with loop structure.

   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:: IterativePlannerAgent

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


   Agent that creates iterative processing plans.


   .. py:method:: build_graph()

      Build iterative planning graph.



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

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


   Structured analysis of query for routing decisions.

   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:: QueryAnalyzerAgent

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


   Agent that performs structured query analysis for routing.


   .. py:method:: build_graph()

      Build query analysis graph.



.. py:class:: QueryComplexity

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


   Query complexity levels for routing decisions.

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


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

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


   Final routing decision with execution plan.

   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:: RoutingDecisionAgent

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


   Agent that makes final routing decisions.


   .. py:method:: build_graph()

      Build routing decision graph.



.. py:class:: RoutingStrategy

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


   Available routing strategies.

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


.. py:class:: SelfRouteRAGAgent

   Bases: :py:obj:`haive.agents.multi.base.SequentialAgent`


   Complete Self-Route RAG agent with structured analysis and iterative planning.


   .. py:method:: from_documents(documents, llm_config = None, analysis_depth = 'comprehensive', max_iterations = 3, enable_fallback = True, **kwargs)
      :classmethod:


      Create Self-Route RAG agent from documents.

      :param documents: Documents to index
      :param llm_config: LLM configuration
      :param analysis_depth: Depth of query analysis
      :param max_iterations: Maximum iterations for planning
      :param enable_fallback: Whether to enable fallback routing
      :param \*\*kwargs: Additional arguments

      :returns: SelfRouteRAGAgent instance



.. py:function:: create_self_route_rag_agent(documents, llm_config = None, routing_mode = 'adaptive', **kwargs)

   Create a Self-Route RAG agent.

   :param documents: Documents for retrieval
   :param llm_config: LLM configuration
   :param routing_mode: Routing mode ("conservative", "adaptive", "aggressive")
   :param \*\*kwargs: Additional arguments

   :returns: Configured Self-Route RAG agent


.. py:function:: get_self_route_rag_io_schema()

   Get I/O schema for Self-Route RAG agents.