primeqa.ir.dense.colbert_top.colbert.search.index_storage.IndexScorer#

class primeqa.ir.dense.colbert_top.colbert.search.index_storage.IndexScorer(index_path, use_gpu)#

Bases: primeqa.ir.dense.colbert_top.colbert.search.index_loader.IndexLoader, primeqa.ir.dense.colbert_top.colbert.search.candidate_generation.CandidateGeneration

Methods

`embedding_ids_to_pids`
`generate_candidate_eids`
`generate_candidate_pids`
`generate_candidate_scores`
`generate_candidates`
`get_cells`
`lookup_eids`
`lookup_pids`
`rank`
`retrieve`
`score_pids`	Always supply a flat list or tensor for pids.
`try_load_torch_extensions`

Attributes

`config`
`metadata`
`num_chunks`
`num_embeddings`

score_pids(config, Q, pids, centroid_scores)#

Always supply a flat list or tensor for pids.

Supply sizes Q = (1 | num_docs, , dim) and D = (num_docs, *, dim). If Q.size(0) is 1, the matrix will be compared with all passages. Otherwise, each query matrix will be compared against the *aligned passage.