WpfVdZddlZddlmZddlmZddlmZddlmZddl m Z ddl m Z dd l mZdd lmZdd lmZdd lmZdd lmZddlmZejZejZe jZ e j!Z"ej#Z$dZ%dZ&dZ'dZ(dZ)ej*GddZ+Gddej,Z-dS)zMediaPipe text embedder task.N)Optional)packet_creator) packet_getter)embeddings_pb2)embedder_options_pb2)text_embedder_graph_options_pb2)embedding_resultcosine_similarity base_options) task_info) doc_controls)base_text_task_apiembeddings_out EMBEDDINGStext_inTEXTz4mediapipe.tasks.text.text_embedder.TextEmbedderGraphcxeZdZUdZeed<dZeeed<dZ eeed<e j de fdZ dS)TextEmbedderOptionsaOptions for the text embedder task. Attributes: base_options: Base options for the text embedder task. l2_normalize: Whether to normalize the returned feature vector with L2 norm. Use this option only if the model does not already contain a native L2_NORMALIZATION TF Lite Op. In most cases, this is already the case and L2 norm is thus achieved through TF Lite inference. quantize: Whether the returned embedding should be quantized to bytes via scalar quantization. Embeddings are implicitly assumed to be unit-norm and therefore any dimension is guaranteed to have a value in [-1.0, 1.0]. Use the l2_normalize option if this is not the case. r N l2_normalizequantizereturnc|j}t|j|j}t ||S)z1Generates an TextEmbedderOptions protobuf object.)rr)r embedder_options)r to_pb2_EmbedderOptionsProtorr_TextEmbedderGraphOptionsProto)selfbase_options_protoembedder_options_protos i/var/www/html/nettyfy-visnx/env/lib/python3.11/site-packages/mediapipe/tasks/python/text/text_embedder.pyrzTextEmbedderOptions.to_pb2?sZ*11332&@@@ *'/ 1 1 11)__name__ __module__ __qualname____doc__ _BaseOptions__annotations__rrboolrrdo_not_generate_docsrrr#r"rr,s  !%,%%%!(HTN!!!$14111%$111r#rceZdZdZededdfdZededdfdZdede fdZ ed e j d e j de fd Zd S) TextEmbedderaoClass that performs embedding extraction on text. This API expects a TFLite model with TFLite Model Metadata that contains the mandatory (described below) input tensors and output tensors. Metadata should contain the input process unit for the model's Tokenizer as well as input / output tensor metadata. Input tensors: (kTfLiteInt32) - 3 input tensors of size `[batch_size x bert_max_seq_len]` with names "ids", "mask", and "segment_ids" representing the input ids, mask ids, and segment ids respectively. - or 1 input tensor of size `[batch_size x max_seq_len]` representing the input ids. At least one output tensor with: (kTfLiteFloat32) - `N` components corresponding to the `N` dimensions of the returned feature vector for this output layer. - Either 2 or 4 dimensions, i.e. `[1 x N]` or `[1 x 1 x 1 x N]`. model_pathrclt|}t|}||S)aCreates an `TextEmbedder` object from a TensorFlow Lite model and the default `TextEmbedderOptions`. Args: model_path: Path to the model. Returns: `TextEmbedder` object that's created from the model file and the default `TextEmbedderOptions`. Raises: ValueError: If failed to create `TextEmbedder` object from the provided file such as invalid file path. RuntimeError: If other types of error occurred. )model_asset_pathr )r(rcreate_from_options)clsr/r optionss r"create_from_model_pathz#TextEmbedder.create_from_model_pathbs8  <<rls$#++++++******IIIIIIOOOOOOWWWWWWddddddEEEEEEKKKKKKEEEEEEJJJJJJ??????,<". !@!Y,<  % .   I 11111111