haive.agents.rag.hyde.agent_v2
==============================

.. py:module:: haive.agents.rag.hyde.agent_v2

.. autoapi-nested-parse::

   HyDE (Hypothetical Document Embeddings) RAG Agent V2.

   Bridges query-document semantic gap by generating hypothetical documents.
   This version properly embeds the hypothetical document for retrieval.



Classes
-------

.. autoapisummary::

   haive.agents.rag.hyde.agent_v2.HyDERAGAgentV2
   haive.agents.rag.hyde.agent_v2.HyDERetrieverAgent


Functions
---------

.. autoapisummary::

   haive.agents.rag.hyde.agent_v2.build_graph
   haive.agents.rag.hyde.agent_v2.transform_to_query


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

.. py:class:: HyDERAGAgentV2

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


   HyDE RAG using hypothetical document generation for better retrieval.

   This version properly uses the hypothetical document as the basis for retrieval.


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


      Create HyDE RAG from documents.

      :param documents: Documents to index
      :param llm_config: Optional LLM configuration
      :param embedding_model: Optional embedding model for vector store
      :param \*\*kwargs: Additional arguments

      :returns: HyDERAGAgentV2 instance



.. py:class:: HyDERetrieverAgent

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


   Custom retriever that uses hypothetical document for enhanced retrieval.


   .. py:method:: build_graph()

      Build graph that passes hypothetical doc as query.



.. py:function:: build_graph()

   Build custom graph for HyDE workflows.

   :returns: Graph configuration or None for default behavior


.. py:function:: transform_to_query(hypothesis)

   Transform hypothesis to query format.

   :param hypothesis: Generated hypothesis text

   :returns: Formatted query string