haive.agents.rag.fusion.agent
=============================

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

.. autoapi-nested-parse::

   RAG Fusion Agents.

   from typing import Any
   Implementation of RAG Fusion with reciprocal rank fusion for enhanced retrieval.
   Based on the architecture pattern from rag-architectures-flows.md.



Classes
-------

.. autoapisummary::

   haive.agents.rag.fusion.agent.FusionResult
   haive.agents.rag.fusion.agent.MultiQueryRetrievalAgent
   haive.agents.rag.fusion.agent.QueryVariationsFusion
   haive.agents.rag.fusion.agent.RAGFusionAgent
   haive.agents.rag.fusion.agent.ReciprocalRankFusionAgent


Functions
---------

.. autoapisummary::

   haive.agents.rag.fusion.agent.create_multi_query_retrieval_callable
   haive.agents.rag.fusion.agent.create_rag_fusion_agent
   haive.agents.rag.fusion.agent.get_rag_fusion_io_schema


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

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

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


   Results from reciprocal rank fusion.

   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:: MultiQueryRetrievalAgent

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


   Agent that uses a callable node for multi-query retrieval - proper Pydantic approach.


   .. py:method:: build_graph()

      Build multi-query retrieval graph with callable node using Pydantic fields.



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

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


   Enhanced query variations for fusion.

   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:: RAGFusionAgent

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


   Complete RAG Fusion agent with query expansion and RRF.


   .. py:method:: from_documents(documents, llm_config = None, embedding_model = None, num_variations = 3, k_parameter = 60.0, **kwargs)
      :classmethod:


      Create RAG Fusion agent from documents.

      :param documents: Documents to index
      :param llm_config: LLM configuration
      :param embedding_model: Embedding model for retrieval
      :param num_variations: Number of query variations to generate
      :param k_parameter: RRF k parameter
      :param \*\*kwargs: Additional arguments

      :returns: RAGFusionAgent instance



.. py:class:: ReciprocalRankFusionAgent

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


   Agent that performs reciprocal rank fusion on multiple retrieval results.


   .. py:method:: build_graph()

      Build RRF fusion graph.



.. py:function:: create_multi_query_retrieval_callable(documents, embedding_model = None, max_docs_per_query = 10)

   Create a callable function for multi-query retrieval that can be used as a graph node.


.. py:function:: create_rag_fusion_agent(documents, llm_config = None, fusion_type = 'standard', **kwargs)

   Create a RAG Fusion agent.

   :param documents: Documents for retrieval
   :param llm_config: LLM configuration
   :param fusion_type: Type of fusion ("standard", "aggressive", "conservative")
   :param \*\*kwargs: Additional arguments

   :returns: Configured RAG Fusion agent


.. py:function:: get_rag_fusion_io_schema()

   Get I/O schema for RAG Fusion agents.