haive.agents.rag.flare.agent
============================

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

.. autoapi-nested-parse::

   FLARE (Forward-Looking Active REtrieval) RAG Agents.

   from typing import Any
   Implementation of FLARE RAG with forward-looking retrieval and iterative generation.
   Uses structured output models for planning and managing active retrieval decisions.



Classes
-------

.. autoapisummary::

   haive.agents.rag.flare.agent.ActiveRetrievalAgent
   haive.agents.rag.flare.agent.ConfidenceLevel
   haive.agents.rag.flare.agent.FLAREPlan
   haive.agents.rag.flare.agent.FLAREPlannerAgent
   haive.agents.rag.flare.agent.FLARERAGAgent
   haive.agents.rag.flare.agent.FLAREResult
   haive.agents.rag.flare.agent.RetrievalDecision


Functions
---------

.. autoapisummary::

   haive.agents.rag.flare.agent.create_active_retrieval_callable
   haive.agents.rag.flare.agent.create_flare_planner_callable
   haive.agents.rag.flare.agent.create_flare_rag_agent
   haive.agents.rag.flare.agent.get_flare_rag_io_schema


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

.. py:class:: ActiveRetrievalAgent

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


   Agent that performs active retrieval based on FLARE plans.


   .. py:method:: build_graph()

      Build active retrieval graph.



.. py:class:: ConfidenceLevel

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


   Confidence levels for generation.

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


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

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


   Forward-looking plan for active retrieval.

   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:: FLAREPlannerAgent

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


   Agent that creates FLARE plans for iterative generation and active retrieval.


   .. py:method:: build_graph()

      Build FLARE planning graph.



.. py:class:: FLARERAGAgent

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


   Complete FLARE RAG agent with forward-looking active retrieval.


   .. py:method:: from_documents(documents, llm_config = None, max_iterations = 5, confidence_threshold = 0.7, **kwargs)
      :classmethod:


      Create FLARE RAG agent from documents.

      :param documents: Documents to index
      :param llm_config: LLM configuration
      :param max_iterations: Maximum FLARE iterations
      :param confidence_threshold: Confidence threshold for retrieval
      :param \*\*kwargs: Additional arguments

      :returns: FLARERAGAgent instance



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

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


   Results from FLARE processing.

   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:: RetrievalDecision

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


   Decisions for active retrieval.

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


.. py:function:: create_active_retrieval_callable(documents, embedding_model = None)

   Create callable function for active retrieval.


.. py:function:: create_flare_planner_callable(llm_config)

   Create callable function for FLARE planning.


.. py:function:: create_flare_rag_agent(documents, llm_config = None, flare_mode = 'adaptive', **kwargs)

   Create a FLARE RAG agent.

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

   :returns: Configured FLARE RAG agent


.. py:function:: get_flare_rag_io_schema()

   Get I/O schema for FLARE RAG agents.