Image parser.

A class that represents a remote ClipEmbedding service.

Image parser. Extract text from images using DONUT or pytesseract.

Base class for Multi Modal embeddings.

Class for RemoteHuggingFaceEmbedding embeddings.

Implements Metadata Filtering.

Default file metadata function wrapper which stores the fs. Allows for pickling of the function.

Convert between text-label and text-index

Simple custom Vector Store. Stores documents in a simple in-memory dict.

Convert between text-label and text-index

The post process for Differentiable Binarization (DB).

decode image

format gray scale image's channel: (3,h,w) -> (1,h,w) Args: inverse: inverse gray image

resize image by target_size and max_size Args: target_size (int): the target size of image keep_ratio (bool): whether keep_ratio o

normalize image such as substract mean, divide std

padding image for model with FPN, instead PadBatch(pad_to_stride) in original config Args: stride (bool): model with FPN need image shape

permute image Args: to_bgr (bool): whether convert RGB to BGR channel_first (bool): whether convert HWC to CHW

Base class for RemoteClipEmbedding Multi Modal embeddings.

Class for RemoteHuggingFaceEmbedding embeddings.

normalize image Args: mean (list): im - mean std (list): im / std is_scale (bool): whether need im / 255 norm_type

convert hwc image to chw image

VectorStore2 (add/get/delete implemented).

Implements semantic/dense search.