emily.index_classes.VectorIndex
===============================

.. py:module:: emily.index_classes.VectorIndex

.. autoapi-nested-parse::

   Created on Thu May  7 10:28:31 2026

   @author: Dr Peter J Bleackley



Classes
-------

.. autoapisummary::

   emily.index_classes.VectorIndex.VectorIndex


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

.. py:class:: VectorIndex(model_url: str, path: str, collection_name: str)

   Uses an embedding model and a vector database to find semantically similar
   candidates


   .. py:attribute:: model


   .. py:attribute:: collection_name


   .. py:attribute:: db


   .. py:method:: init_db()
      :async:


      Creates collection for vectors if it does not already exists

      :rtype: None.



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


      Adds documents to database

      :param corpus: Iterable containing (filename,text) for documents to be added.
      :type corpus: AsyncIterable[tuple[str,str]]

      :rtype: None.



   .. py:method:: __call__(query: str, limit: int = 10) -> polars.LazyFrame
      :async:


      Searches the vector database for documents relevant to query

      :param query: Search query
      :type query: str
      :param limit: Maximimum number of results to return. The default is 10.
      :type limit: int, optional

      :returns: LazyFrame containing filenames of matching documents
      :rtype: pl.LazyFrame



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


      Clears data from vector database

      :rtype: None.