haive.agents.rag.multi_query.agent
==================================

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

.. autoapi-nested-parse::

   Multi-Query RAG Agent.

   Improves recall through query diversification.
   Generates multiple query variations and retrieves from all.



Classes
-------

.. autoapisummary::

   haive.agents.rag.multi_query.agent.MultiQueryRAGAgent
   haive.agents.rag.multi_query.agent.MultiRetrievalAgent
   haive.agents.rag.multi_query.agent.QueryVariations


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

.. py:class:: MultiQueryRAGAgent

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


   Multi-Query RAG with query expansion for improved recall.


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


      Create Multi-Query 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: MultiQueryRAGAgent instance



.. py:class:: MultiRetrievalAgent

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


   Agent that performs parallel retrieval with multiple queries.


   .. py:method:: build_graph()

      Build graph that retrieves with multiple queries in parallel.



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

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


   Structured output for query variations.

   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.