haive.agents.rag.query_planning.agent
=====================================

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

.. autoapi-nested-parse::

   Query Planning Agentic RAG Agent.

   from typing import Any
   Implementation of query planning RAG with structured decomposition and execution.
   Provides intelligent query analysis, planning, and multi-stage retrieval strategies.



Classes
-------

.. autoapisummary::

   haive.agents.rag.query_planning.agent.QueryComplexity
   haive.agents.rag.query_planning.agent.QueryPlan
   haive.agents.rag.query_planning.agent.QueryPlanningRAGAgent
   haive.agents.rag.query_planning.agent.QueryPlanningResult
   haive.agents.rag.query_planning.agent.QueryType
   haive.agents.rag.query_planning.agent.SubQuery
   haive.agents.rag.query_planning.agent.SubQueryResult


Functions
---------

.. autoapisummary::

   haive.agents.rag.query_planning.agent.create_query_planning_rag_agent
   haive.agents.rag.query_planning.agent.get_query_planning_rag_io_schema


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

.. py:class:: QueryComplexity

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


   Query complexity levels.

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


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

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


   Complete query 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:: QueryPlanningRAGAgent

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


   Query Planning RAG agent with structured decomposition and execution.

   This agent uses conditional edges to execute sub-queries in a planned order.


   .. py:method:: build_graph()

      Build the query planning graph with conditional edges.



   .. py:method:: create_query_plan(state)

      Create a query execution plan.



   .. py:method:: execute_sub_query(state)

      Execute the current sub-query.



   .. py:method:: from_documents(documents, llm_config = None, planning_depth = 3, **kwargs)
      :classmethod:


      Create Query Planning RAG agent from documents.

      :param documents: Documents to index for retrieval
      :param llm_config: LLM configuration
      :param planning_depth: Maximum depth of query decomposition
      :param \*\*kwargs: Additional arguments

      :returns: QueryPlanningRAGAgent instance



   .. py:method:: setup_agent()

      Initialize engines.



   .. py:method:: should_continue_execution(state)

      Determine if more sub-queries should be executed.



   .. py:method:: synthesize_results(state)

      Synthesize sub-query results into final answer.



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

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


   Complete result from query planning 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:: QueryType

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


   Types of queries for planning.

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


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

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


   Individual sub-query in a decomposed 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:: SubQueryResult(/, **data)

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


   Result from executing a sub-query.

   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_planning_rag_agent(documents, llm_config = None, planning_mode = 'comprehensive', **kwargs)

   Create a Query Planning RAG agent.

   :param documents: Documents for retrieval
   :param llm_config: LLM configuration
   :param planning_mode: Planning mode ("simple", "moderate", "comprehensive")
   :param \*\*kwargs: Additional arguments

   :returns: Configured Query Planning RAG agent


.. py:function:: get_query_planning_rag_io_schema()

   Get I/O schema for Query Planning RAG agents.