ExactSearcher

class lightning_ir.retrieve.base.searcher.ExactSearcher(index_dir: Path | str, search_config: SearchConfig, module: BiEncoderModule, use_gpu: bool = True)

Bases: Searcher

Searcher that retrieves documents using exact matching of query embeddings.

Methods

search(output)

Search for documents based on the output of the bi-encoder model.

Attributes

doc_token_idcs

Get the document token indices for scoring.

property doc_token_idcs: Tensor

Get the document token indices for scoring.

Returns:

The document token indices.

Return type:

torch.Tensor

search(output: BiEncoderOutput) → Tuple[PackedTensor, List[List[str]]]

Search for documents based on the output of the bi-encoder model.

Parameters:

output (BiEncoderOutput) – The output from the bi-encoder model containing query and document embeddings.

Returns:

The top-k scores and corresponding document IDs.

Return type:

Tuple[PackedTensor, List[List[str]]]