haive.agents.rag.speculative.agent
==================================

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

.. autoapi-nested-parse::

   Speculative RAG Agents.

   from typing import Any
   Implementation of speculative RAG with parallel hypothesis generation and verification.
   Uses structured output models for hypothesis planning and iterative refinement.



Classes
-------

.. autoapisummary::

   haive.agents.rag.speculative.agent.Hypothesis
   haive.agents.rag.speculative.agent.HypothesisConfidence
   haive.agents.rag.speculative.agent.HypothesisGeneratorAgent
   haive.agents.rag.speculative.agent.ParallelVerificationAgent
   haive.agents.rag.speculative.agent.SpeculativeExecutionPlan
   haive.agents.rag.speculative.agent.SpeculativeRAGAgent
   haive.agents.rag.speculative.agent.SpeculativeResult
   haive.agents.rag.speculative.agent.VerificationStatus


Functions
---------

.. autoapisummary::

   haive.agents.rag.speculative.agent.create_speculative_rag_agent
   haive.agents.rag.speculative.agent.get_speculative_rag_io_schema


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

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

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


   Individual hypothesis with structured metadata.

   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:: HypothesisConfidence

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


   Confidence levels for hypotheses.

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


.. py:class:: HypothesisGeneratorAgent

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


   Agent that generates multiple hypotheses for speculative reasoning.


   .. py:method:: build_graph()

      Build hypothesis generation graph.



.. py:class:: ParallelVerificationAgent

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


   Agent that performs parallel hypothesis verification.


   .. py:method:: build_graph()

      Build parallel verification graph.



   .. py:method:: model_post_init(__context)

      Initialize the mixin with state tracking attributes after Pydantic validation.



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

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


   Plan for executing speculative retrieval and verification.

   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:: SpeculativeRAGAgent

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


   Complete Speculative RAG agent with parallel hypothesis processing.


   .. py:method:: from_documents(documents, llm_config = None, num_hypotheses = 5, verification_depth = 'thorough', **kwargs)
      :classmethod:


      Create Speculative RAG agent from documents.

      :param documents: Documents to index
      :param llm_config: LLM configuration
      :param num_hypotheses: Number of hypotheses to generate
      :param verification_depth: Depth of verification process
      :param \*\*kwargs: Additional arguments

      :returns: SpeculativeRAGAgent instance



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

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


   Results from speculative RAG 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:: VerificationStatus

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


   Status of hypothesis verification.

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


.. py:function:: create_speculative_rag_agent(documents, llm_config = None, speculation_mode = 'balanced', **kwargs)

   Create a Speculative RAG agent.

   :param documents: Documents for retrieval
   :param llm_config: LLM configuration
   :param speculation_mode: Mode ("conservative", "balanced", "aggressive")
   :param \*\*kwargs: Additional arguments

   :returns: Configured Speculative RAG agent


.. py:function:: get_speculative_rag_io_schema()

   Get I/O schema for Speculative RAG agents.