abacusai.document_retriever_config
==================================

.. py:module:: abacusai.document_retriever_config


Classes
-------

.. autoapisummary::

   abacusai.document_retriever_config.DocumentRetrieverConfig


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

.. py:class:: DocumentRetrieverConfig(client, chunkSize=None, chunkOverlapFraction=None, textEncoder=None, scoreMultiplierColumn=None, pruneVectors=None, indexMetadataColumns=None, useDocumentSummary=None, summaryInstructions=None)

   Bases: :py:obj:`abacusai.return_class.AbstractApiClass`


   A config for document retriever creation.

   :param client: An authenticated API Client instance
   :type client: ApiClient
   :param chunkSize: The size of chunks for vector store, i.e., maximum number of words in the chunk.
   :type chunkSize: int
   :param chunkOverlapFraction: The fraction of overlap between two consecutive chunks.
   :type chunkOverlapFraction: float
   :param textEncoder: The text encoder used to encode texts in the vector store.
   :type textEncoder: str
   :param scoreMultiplierColumn: The values in this metadata column are used to modify the relevance scores of returned chunks.
   :type scoreMultiplierColumn: str
   :param pruneVectors: Corpus specific transformation of vectors that applies dimensional reduction techniques to strip common components from the vectors.
   :type pruneVectors: bool
   :param indexMetadataColumns: If True, metadata columns of the FG will also be used for indexing and querying.
   :type indexMetadataColumns: bool
   :param useDocumentSummary: If True, uses the summary of the document in addition to chunks of the document for indexing and querying.
   :type useDocumentSummary: bool
   :param summaryInstructions: Instructions for the LLM to generate the document summary.
   :type summaryInstructions: str


   .. py:attribute:: chunk_size
      :value: None



   .. py:attribute:: chunk_overlap_fraction
      :value: None



   .. py:attribute:: text_encoder
      :value: None



   .. py:attribute:: score_multiplier_column
      :value: None



   .. py:attribute:: prune_vectors
      :value: None



   .. py:attribute:: index_metadata_columns
      :value: None



   .. py:attribute:: use_document_summary
      :value: None



   .. py:attribute:: summary_instructions
      :value: None



   .. py:attribute:: deprecated_keys


   .. py:method:: __repr__()


   .. py:method:: to_dict()

      Get a dict representation of the parameters in this class

      :returns: The dict value representation of the class parameters
      :rtype: dict