towhee.hub.builtin.operators.faiss_search.faiss_search

class towhee.hub.builtin.operators.faiss_search.faiss_search(findex, **kwargs)

Bases: object

Search for embedding vectors in Faiss. Note that the index has data before searching, refer to DataCollection Mixin to_faiss.

Parameters:

• findex (str or faiss.INDEX) – The path to faiss index file(defaults to ‘./index.bin’) or faiss index.

• kwargs – The kwargs with index.search, refer to https://github.com/facebookresearch/faiss/wiki. And the parameter k defaults to 10.

Examples: ``` import towhee res = (

towhee.glob[‘path’](‘./*.jpg’)

.image_decode[‘path’, ‘img’]() .image_embedding.timm[‘img’, ‘vec’](model_name=’resnet50’) .faiss_search[‘vec’, ‘results’](findex=’./faiss/faiss.index’) .to_list()

Methods

Attributes

metainfo

__call__(*args, **kws)

Call self as a function.

__init__(findex, **kwargs)