WiFddlZddlmZddlmZddlmZGddeZy)N)tqdm)List) BaseEmbeddercReZdZdZfdZddeededejfdZ xZ S) USEBackendaUniversal Sentence Encoder. USE encodes text into high-dimensional vectors that are used for semantic similarity in BERTopic. Arguments: embedding_model: An USE embedding model Examples: ```python import tensorflow_hub from bertopic.backend import USEBackend embedding_model = tensorflow_hub.load("https://tfhub.dev/google/universal-sentence-encoder/4") use_embedder = USEBackend(embedding_model) ``` ctt| |dg||_y#t$r t dwxYw)Nz test sentencezsPlease select a correct USE model: `import tensorflow_hub` `embedding_model = tensorflow_hub.load(path_to_model)`)super__init__embedding_model TypeError ValueError)selfr __class__s a/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/backend/_use.pyr zUSEBackend.__init__sH   _- .#2D  I  s"7 documentsverbosereturnctjt|| Dcgc]3}|j|gj j d5c}}|Scc}w)aEmbed a list of n documents/words into an n-dimensional matrix of embeddings. Arguments: documents: A list of documents or words to be embedded verbose: Controls the verbosity of the process Returns: Document/words embeddings with shape (n, m) with `n` documents/words that each have an embeddings size of `m` )disabler)nparrayrr cpunumpy)rrrdoc embeddingss rembedzUSEBackend.embed(s]XXEI)ah]hEi jcT ! !3% ( , , . 4 4 6q 9 j  ks8A!)F) __name__ __module__ __qualname____doc__r rstrboolrndarrayr __classcell__)rs@rrrs/$ tCy4BJJr)rrrtypingrbertopic.backendrrr%rr)s)//r%