Wi VddlZddlmZmZddlmZddlmZddl m Z Gdde Z y)N)ListUnion)SentenceTransformer)StaticEmbedding) BaseEmbeddercheZdZdZd deeefdeffd Zd de edede jfdZ xZ S) SentenceTransformerBackendaSentence-transformers embedding model. The sentence-transformers embedding model used for generating document and word embeddings. Arguments: embedding_model: A sentence-transformers embedding model model2vec: Indicates whether `embedding_model` is a model2vec model. NOTE: Only works if `embedding_model` is a string. Otherwise, you can pass the model2vec model directly to `embedding_model`. Examples: To create a model, you can load in a string pointing to a sentence-transformers model: ```python from bertopic.backend import SentenceTransformerBackend sentence_model = SentenceTransformerBackend("all-MiniLM-L6-v2") ``` or you can instantiate a model yourself: ```python from bertopic.backend import SentenceTransformerBackend from sentence_transformers import SentenceTransformer embedding_model = SentenceTransformer("all-MiniLM-L6-v2") sentence_model = SentenceTransformerBackend(embedding_model) ``` If you want to use a model2vec model without having to install model2vec, you can pass the model2vec model as a string: ```python from bertopic.backend import SentenceTransformerBackend from sentence_transformers import SentenceTransformer embedding_model = SentenceTransformer("minishlab/potion-base-8M", model2vec=True) sentence_model = SentenceTransformerBackend(embedding_model) ``` embedding_model model2vecc8t|d|_|r8t|tr(t j |}t|g|_yt|tr||_yt|trt||_||_ytd)N)moduleszPlease select a correct SentenceTransformers model: `from sentence_transformers import SentenceTransformer` `model = SentenceTransformer('all-MiniLM-L6-v2')`) super__init__ _hf_model isinstancestrrfrom_model2vecrr ValueError)selfr r static_embedding __class__s r/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/backend/_sentencetransformers.pyrz#SentenceTransformerBackend.__init__5s  OS9.==oN #6@P?Q#RD )< =#2D  -#6#GD ,DND  documentsverbosereturnc@|jj||}|S)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` )show_progress_bar)r encode)rrr embeddingss rembedz SentenceTransformerBackend.embedHs%))00g0V r)F)__name__ __module__ __qualname____doc__rrrboolrrnpndarrayr! __classcell__)rs@rr r sJ)Vc3F.F(GTX& tCy 4 BJJ rr ) numpyr'typingrrsentence_transformersrsentence_transformers.modelsrbertopic.backendrr rrr0s"58)LLr