Ë kQêjï ãó€—ddlmZmZmZmZddlZddlmZddl m Z ddl m Z ddl mZe d «Gd „d e ««Zy) é)ÚListÚOptionalÚTupleÚUnionNé)Úattempt_import_or_raiseé)ÚTextEmbeddingFunction)Úregister)Úweak_lruúsentence-transformerscó*‡—eZdZUdZdZeed<dZeed<dZe ed<dZ e ed <d Z e eed <ˆfd „Z d e eee effd„Zed e fd„«Zed„«Zd„Zdeeeej0fd eej2fd„Zed¬«d„«ZˆxZS)ÚSentenceTransformerEmbeddingsa9 An embedding function that uses the sentence-transformers library https://huggingface.co/sentence-transformers Parameters ---------- name : str, default "all-MiniLM-L6-v2" The name of the model to use. device : str, default "cpu" The device to use for the model normalize : bool, default True Whether to normalize the embeddings trust_remote_code : bool, default False Whether to run code from the model's repository. Only enable this for repositories you trust. When restored from table metadata, this is only enabled for models allowed with [allow_remote_code][lancedb.embeddings.EmbeddingFunctionRegistry.allow_remote_code]. revision : Optional[str], default None The model revision to load, such as a commit hash. zall-MiniLM-L6-v2ÚnameÚcpuÚdeviceTÚ normalizeFÚtrust_remote_codeNÚrevisionc ó2•—t‰|di|¤Žd|_y)N©)ÚsuperÚ__init__Ú_ndims)ÚselfÚkwargsÚ __class__s €úm/home/oem/CyberBrain26-unified/.venv/lib/python3.12/site-packages/lancedb/embeddings/sentence_transformers.pyrz&SentenceTransformerEmbeddings.__init__-sø€Ü ‰ÑÑ"˜6Ò"؈ óÚreturncó2—|j|jfS)N)rr©rs rÚremote_code_modelz/SentenceTransformerEmbeddings.remote_code_model1s€Ø— ‘ ˜4Ÿ=™=Ð)Ð)rcó—y)NTr)Úclss rÚ!_legacy_trust_remote_code_defaultz?SentenceTransformerEmbeddings._legacy_trust_remote_code_default4s€àrcó"—|j«S)zÇ Get the sentence-transformers embedding model specified by the name, device, and trust_remote_code. This is cached so that the model is only loaded once per process. )Úget_embedding_modelr"s rÚembedding_modelz-SentenceTransformerEmbeddings.embedding_model8s€ð×'Ñ'Ó)Ð)rcóv—|j€"t|jd«d«|_|jS)NÚfoor)rÚlenÚgenerate_embeddingsr"s rÚndimsz#SentenceTransformerEmbeddings.ndimsAs2€Ø ;‰;Рܘd×6Ñ6°uÓ=¸aÑ@ÓAˆDŒKØ{‰{ÐrÚtextscó€—|jjt|«d|j¬«j «S)z® Get the embeddings for the given texts Parameters ---------- texts: list[str] or np.ndarray (of str) The texts to embed T)Úconvert_to_numpyÚnormalize_embeddings)r)ÚencodeÚlistrÚtolist)rr/s rr-z1SentenceTransformerEmbeddings.generate_embeddingsFs<€ð×#Ñ#×*Ñ*Ü ‹KØ!Ø!%§¡ð+ó ÷ ‰&‹(ð  rr )Úmaxsizecó”—tdd«}|j|j|j|j|j ¬«S)a Get the sentence-transformers embedding model specified by the name, device, and trust_remote_code. This is cached so that the model is only loaded once per process. TODO: use lru_cache instead with a reasonable/configurable maxsize Úsentence_transformersr )rrr)rÚSentenceTransformerrrrr)rr8s rr(z1SentenceTransformerEmbeddings.get_embedding_modelWsM€ô!8Ø #Ð%<ó! Ðð%×8Ñ8Ø I‰IØ—;‘;Ø"×4Ñ4Ø—]‘]ð 9ó ð r)Ú__name__Ú __module__Ú __qualname__Ú__doc__rÚstrÚ__annotations__rrÚboolrrrrrr#Ú classmethodr&Úpropertyr)r.rrÚnpÚndarrayÚarrayr-r r(Ú __classcell__)rs@rrrsáø…ñð,#€Dˆ#Ó"Ø€FˆCÓØ€IˆtÓØ#ÐtÓ#Ø"€Hˆhs‰mÓ"ôð* 8¨E°#°xÀ±}Ð2DÑ,EÑ#Fó*ðð°$òóððñ*óð*òð ؘ4 ™9 b§j¡jÐ0Ñ1ðà ˆbh‰h‰óñ"aÔñ óô rr)ÚtypingrrrrÚnumpyrCÚutilrÚbaser Úregistryr Úutilsr rrrrúrMsAð÷ 0Ó/ãå*Ý'ÝÝñ Ð !Ó"ôX Ð$9óX ó#ñX r