Retriever#

Vecworks implements various retrievers for interfacing with vector stores.

class vecworks.retrievers.generic.Retriever#

Pypeworks Node providing access to a single vector index for similarity search.

Interface#

__init__(index: Index | list[Index], **kwargs)#

Initializes the retriever. This must be invoked by an sub-class as part of initialization.

exec(input: Any | Iterable, **kwargs)#

Search the index for content similar to the given input.

query(input: Iterable[ndarray | sparray | spmatrix], **kwargs) → dict[str, list[Any]]#

Search the index for a vector similar to the given vector(s). If the input is not yet vectorised, call exec() instead.

Note

Any sub-class must re-implement this method to provide a fully functional retriever.

class vecworks.retrievers.generic.MultiIndexRetriever#

Interface implemented by all retrievers allowing to query multiple indices at the same time.

__init__(index: Index | list[Index], return_rank_as: str | None = None, ensemble_by: ENSEMBLERS | None = None, top_k: int = 10, **kwargs)#

Initializes the retriever. This must be invoked by an sub-class as part of initialization.

index: Index or indices to query for similarity.
return_rank_as: Name to assign to the variable holding the rank.
ensemble_by: Ensembler to use to combine results from similarity queries. Refer to vecworks.functions.ENSEMBLERS for the available options.
top_k: Maximum number of results to retrieve per vector.
kwargs: Any additional arguments to pass to the underlying Pypeworks Node.

exec(*args, **kwargs)#

Search the index for content similar to the given input.

args: Input(s) to compare the index with for similarity, passed without a name.
kwargs: Input(s) to compare the index with for similarity, passed with a name. Any arguments with a name that may not be mapped to an index, are passed as key-value arguments for use at the discretion of the retriever.

query(input: dict[str, Iterable[ndarray | sparray | spmatrix]], **kwargs) → dict[str, list[list[Any]]]#

Search the index for a vector similar to the given vector(s). If the input is not yet vectorised, call exec() instead.

Note

Any sub-class must re-implement this method to provide a fully functional retriever.