emily.index_classes.VectorIndex

Created on Thu May 7 10:28:31 2026

@author: Dr Peter J Bleackley

Classes

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

class emily.index_classes.VectorIndex.VectorIndex(model_url: str, path: str, collection_name: str)[source]

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

async init_db()[source]

Creates collection for vectors if it does not already exists

async add_documents(corpus: collections.abc.AsyncIterable[tuple[str, str]])[source]

Adds documents to database

Parameters:: corpus (AsyncIterable[tuple[str,str]]) – Iterable containing (filename,text) for documents to be added.
Return type:: None.

async __call__(query: str, limit: int = 10) → polars.LazyFrame[source]

Searches the vector database for documents relevant to query

Parameters:

query (str) – Search query
limit (int, optional) – Maximimum number of results to return. The default is 10.

Returns:

LazyFrame containing filenames of matching documents

Return type:

pl.LazyFrame

async clear()[source]

Clears data from vector database