gnes.indexer.chunk.numpy module

class gnes.indexer.chunk.numpy.NumpyIndexer(is_binary=False, *args, **kwargs)

Bases: gnes.indexer.base.BaseChunkIndexer

An exhaustive search indexer using numpy The distance is computed as L1 distance normalized by the number of dimension

add(keys, vectors, weights, *args, **kwargs)

adding new chunks and their vector representations

Parameters:

• keys (List[Tuple[int, Any]]) – list of (doc_id, offset) tuple
• vectors (ndarray) – vector representations
• weights (List[float]) – weight of the chunks

query(keys, top_k, *args, **kwargs)

Return type:List[List[Tuple]]

train(*args, **kwargs)

Train the model, need to be overrided