haive.agents.rag.self_reflective.agent
======================================

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

.. autoapi-nested-parse::

   Self-Reflective Agentic RAG Agent.

   from typing import Any
   Implementation of self-reflective RAG with critique and iterative improvement.
   Uses reflection loops to assess and enhance answer quality.



Classes
-------

.. autoapisummary::

   haive.agents.rag.self_reflective.agent.ImprovedAnswer
   haive.agents.rag.self_reflective.agent.ReflectionCritique
   haive.agents.rag.self_reflective.agent.ReflectionPlan
   haive.agents.rag.self_reflective.agent.ReflectionType
   haive.agents.rag.self_reflective.agent.SelfReflectiveRAGAgent
   haive.agents.rag.self_reflective.agent.SelfReflectiveResult


Functions
---------

.. autoapisummary::

   haive.agents.rag.self_reflective.agent.create_self_reflective_rag_agent
   haive.agents.rag.self_reflective.agent.get_self_reflective_rag_io_schema


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

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

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


   Result of answer improvement iteration.

   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:: ReflectionCritique(/, **data)

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


   Structured critique from reflection.

   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:: ReflectionPlan(/, **data)

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


   Plan for iterative improvement based on reflection.

   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:: ReflectionType

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


   Types of reflection analysis.

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


.. py:class:: SelfReflectiveRAGAgent

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


   Self-Reflective RAG agent with iterative improvement capabilities.

   This agent uses conditional edges to iterate through reflection loops.


   .. py:method:: build_graph()

      Build the self-reflective graph with conditional edges.



   .. py:method:: from_documents(documents, llm_config = None, max_iterations = 3, quality_threshold = 0.85, **kwargs)
      :classmethod:


      Create Self-Reflective RAG agent from documents.

      :param documents: Documents to index for retrieval
      :param llm_config: LLM configuration
      :param max_iterations: Maximum reflection iterations
      :param quality_threshold: Quality threshold to stop iterating
      :param \*\*kwargs: Additional arguments

      :returns: SelfReflectiveRAGAgent instance



   .. py:method:: generate_initial_answer(state)

      Generate initial answer.



   .. py:method:: improve_answer(state)

      Improve the answer based on reflection.



   .. py:method:: reflect_and_critique(state)

      Generate critiques and plan improvements.



   .. py:method:: setup_agent()

      Initialize engines.



   .. py:method:: should_continue_improving(state)

      Determine if improvement should continue.



   .. py:method:: synthesize_result(state)

      Create final self-reflective result.



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

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


   Complete result from self-reflective RAG process.

   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_self_reflective_rag_agent(documents, llm_config = None, reflection_mode = 'thorough', **kwargs)

   Create a Self-Reflective RAG agent.

   :param documents: Documents for retrieval
   :param llm_config: LLM configuration
   :param reflection_mode: Mode ("quick", "balanced", "thorough")
   :param \*\*kwargs: Additional arguments

   :returns: Configured Self-Reflective RAG agent


.. py:function:: get_self_reflective_rag_io_schema()

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