abacusai.api_class.document_retriever
=====================================

.. py:module:: abacusai.api_class.document_retriever


Attributes
----------

.. autoapisummary::

   abacusai.api_class.document_retriever.DocumentRetrieverConfig


Classes
-------

.. autoapisummary::

   abacusai.api_class.document_retriever.VectorStoreConfig


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

.. py:class:: VectorStoreConfig

   Bases: :py:obj:`abacusai.api_class.abstract.ApiClass`


   Config for indexing options of a document retriever. Default values of optional arguments are heuristically selected by the Abacus.AI platform based on the underlying data.

   :param chunk_size: The size of text chunks in the vector store.
   :type chunk_size: int
   :param chunk_overlap_fraction: The fraction of overlap between chunks.
   :type chunk_overlap_fraction: float
   :param text_encoder: Encoder used to index texts from the documents.
   :type text_encoder: VectorStoreTextEncoder
   :param chunk_size_factors: Chunking data with multiple sizes. The specified list of factors are used to calculate more sizes, in addition to `chunk_size`.
   :type chunk_size_factors: list
   :param score_multiplier_column: If provided, will use the values in this metadata column to modify the relevance score of returned chunks for all queries.
   :type score_multiplier_column: str
   :param prune_vectors: Transform vectors using SVD so that the average component of vectors in the corpus are removed.
   :type prune_vectors: bool
   :param index_metadata_columns: If True, metadata columns of the FG will also be used for indexing and querying.
   :type index_metadata_columns: bool
   :param use_document_summary: If True, uses the summary of the document in addition to chunks of the document for indexing and querying.
   :type use_document_summary: bool
   :param summary_instructions: Instructions for the LLM to generate the document summary.
   :type summary_instructions: str
   :param standalone_deployment: If True, the document retriever will be deployed as a standalone deployment.
   :type standalone_deployment: bool


   .. py:attribute:: chunk_size
      :type:  int
      :value: None



   .. py:attribute:: chunk_overlap_fraction
      :type:  float
      :value: None



   .. py:attribute:: text_encoder
      :type:  abacusai.api_class.enums.VectorStoreTextEncoder
      :value: None



   .. py:attribute:: chunk_size_factors
      :type:  list
      :value: None



   .. py:attribute:: score_multiplier_column
      :type:  str
      :value: None



   .. py:attribute:: prune_vectors
      :type:  bool
      :value: None



   .. py:attribute:: index_metadata_columns
      :type:  bool
      :value: None



   .. py:attribute:: use_document_summary
      :type:  bool
      :value: None



   .. py:attribute:: summary_instructions
      :type:  str
      :value: None



   .. py:attribute:: standalone_deployment
      :type:  bool
      :value: False



.. py:data:: DocumentRetrieverConfig

