^Nj!UddlmZmZmZmZddlmZmZddlm Z m Z ddl m Z ddl mZmZddlmZddlmZmZddlmZmZed d d d d ed dedddddeddedddddeddedd dddeddeddddd eddgZeeed <Gd!d"eeeZGd#d$eeZy%)&)AnyIterableSequenceType) NumpyArrayDevice) ImageInput OnnxProvider)OnnxOutputContext)define_cache_dir normalize)ImageEmbeddingBase)ImageEmbeddingWorkerOnnxImageModel)DenseModelDescription ModelSourcezQdrant/clip-ViT-B-32-visioniz4Image embeddings, Multimodal (text&image), 2021 yearmitg(\?)hfz model.onnx)modeldim descriptionlicense size_in_GBsources model_filezQdrant/resnet50-onnxiz-Image embeddings, Unimodal (image), 2016 yearz apache-2.0g?zQdrant/Unicom-ViT-B-16izYImage embeddings (more detailed than Unicom-ViT-B-32), Multimodal (text&image), 2023 yearg= ףp=?zQdrant/Unicom-ViT-B-32z4Image embeddings, Multimodal (text&image), 2023 yeargQ?zjinaai/jina-clip-v1z4Image embeddings, Multimodal (text&image), 2024 yearzonnx/vision_model.onnxsupported_onnx_modelsc`eZdZdddejddddfdededzdedzdeedzde ezde edzd e d edzd edzd e ffd Z ddZ ede efdZ ddeeezdededzd e deef dZededfdZdeeefd e deeeffdZded e deefdZxZS)OnnxImageEmbeddingNF model_name cache_dirthreads providerscuda device_ids lazy_load device_idspecific_model_pathkwargsc  t ||||fi| ||_||_|j | |_||_||_d|_|||_n |j |j d|_|j||_ tt||_ | |_|j|j|j|j |j|_|js|j%yy)a Args: model_name (str): The name of the model to use. cache_dir (str, optional): The path to the cache directory. Can be set using the `FASTEMBED_CACHE_PATH` env variable. Defaults to `fastembed_cache` in the system's temp directory. threads (int, optional): The number of threads single onnxruntime session can use. Defaults to None. providers (Optional[Sequence[OnnxProvider]], optional): The list of onnxruntime providers to use. Mutually exclusive with the `cuda` and `device_ids` arguments. Defaults to None. cuda (Union[bool, Device], optional): Whether to use cuda for inference. Mutually exclusive with `providers` Defaults to Device.AUTO. device_ids (Optional[list[int]], optional): The list of device ids to use for data parallel processing in workers. Should be used with `cuda` equals to `True`, `Device.AUTO` or `Device.CUDA`, mutually exclusive with `providers`. Defaults to None. lazy_load (bool, optional): Whether to load the model during class initialization or on demand. Should be set to True when using multiple-gpu and parallel encoding. Defaults to False. device_id (Optional[int], optional): The device id to use for loading the model in the worker process. specific_model_path (Optional[str], optional): The specific path to the onnx model dir if it should be imported from somewhere else Raises: ValueError: If the model_name is not in the format / e.g. BAAI/bge-base-en. Nr)local_files_onlyr')super__init__r"r%_select_exposed_session_options_extra_session_optionsr$r#r&_get_model_descriptionmodel_descriptionstrr r _specific_model_pathdownload_model_local_files_only _model_dirload_onnx_model) selfrr r!r"r#r$r%r&r'r( __class__s o/Users/ahmed/devFolder/Ultron/claude-voice/.venv/lib/python3.12/site-packages/fastembed/image/onnx_embedding.pyr,zOnnxImageEmbedding.__init__?sJ YB6B""&*&J&J6&R#% &*  &DN __ (!__Q/DN!%! 1, data-parallel encoding will be used, recommended for offline encoding of large datasets. If 0, use all available cores. If None, don't use data-parallel processing, use default onnxruntime threading instead. Returns: List of embeddings, one per document ) rr rDrErFr"r#r$r*r'r>N) _embed_imagesrr1r r"r#r$r4r2r.)r7rDrErFr(s r9embedzOnnxImageEmbedding.embeds}.&4%%  $..)!nn!33 $ 9 9"&"="=    sA;B=B>Bz ImageEmbeddingWorker[NumpyArray]ctSN)OnnxImageEmbeddingWorkerrAs r9_get_worker_classz$OnnxImageEmbedding._get_worker_classs''r: onnx_inputc |S)z, Preprocess the onnx input. rH)r7rOr(s r9_preprocess_onnx_inputz)OnnxImageEmbedding._preprocess_onnx_inputs r:outputc ,t|jSrL)r model_output)r7rRr(s r9_post_process_onnx_outputz,OnnxImageEmbedding._post_process_onnx_outputs,,--r:)r;N)N)__name__ __module__ __qualname__rAUTOr1intrr boollistrr,r6 classmethodrrCr rrrJrrNdictrQr rU __classcell__)r8s@r9rr>s !%"37$kk'+ $*.@#@#: @# t @# L)D0 @#Vm@#I$@#@#:@#!4Z@#@#D  %t,A'B%%# $ Xj11$ $ * $  $ *  $ L($'I"J((sJ/;> c:o .'.36. * .r:rc$eZdZdedededefdZy)rMrr r(r;c td||dd|S)N)rr r!rH)r)r7rr r(s r9init_embeddingz'OnnxImageEmbeddingWorker.init_embeddings'! !    r:N)rWrXrYr1rrrdrHr:r9rMrMs$    Pb r:rMN)typingrrrrfastembed.common.typesrrfastembed.commonr r fastembed.common.onnx_modelr fastembed.common.utilsr r $fastembed.image.image_embedding_baser fastembed.image.onnx_image_modelrr"fastembed.common.model_descriptionrrrr]__annotations__rrMrHr:r9rns00659>CQQ+ J<=$ C56& o78& J78# J45+K.6t12.bQ.+^J-GQ.h 3J? r: