emily.index_classes.OkapiIndex
==============================

.. py:module:: emily.index_classes.OkapiIndex

.. autoapi-nested-parse::

   Created on Wed May  6 14:09:33 2026

   @author: Dr Peter J Bleackley



Attributes
----------

.. autoapisummary::

   emily.index_classes.OkapiIndex.stop


Classes
-------

.. autoapisummary::

   emily.index_classes.OkapiIndex.OkapiIndex


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

.. py:data:: stop

.. py:class:: OkapiIndex(config_path: Optional[pathlib.Path] = None)

   Indexes documents using BM25


   .. py:method:: add_documents(corpus: collections.abc.AsyncIterable[tuple[str, list[str]]])
      :async:


      Adds documents to the index and computes the TF component

      :param corpus: Documents to add. Tuple of a filename and a list of strings, which contains the
                     preprocessed (lower cased, punctuation removed) contents of the document
      :type corpus: AsyncIterable[tuple[str,list[str]]]

      :rtype: None.



   .. py:method:: __call__(query: list[str]) -> polars.LazyFrame

      Finds candidate documents with the highest BM25 score. Uses the Pareto
      principal to automatically threhold the results. For N candidate documents
      Np results will be returned, such that the account for (1-p) of the total
      relevance of the sample

      :param query: Parsed query string
      :type query: list[str]

      :returns: LazyFrame containing a single column, "filename"
      :rtype: polars.LazyFrame



   .. py:method:: save(path: pathlib.Path)

      Saves the index to Parquet

      :param path: Filename to save index to.
      :type path: Path

      :rtype: None.



   .. py:method:: clear()
      :async:


      Clears the index

      :rtype: None.