├── .gitignore ├── LICENSE ├── README.md ├── clearedge ├── __init__.py ├── bbox.py ├── chunk.py ├── metadata.py ├── ocr_config │ └── config.yaml ├── reader │ ├── __init__.py │ ├── en_PP-OCRv4_rec_infer.onnx │ └── pdf.py └── utils │ ├── __init__.py │ ├── hf_utils.py │ ├── pdf_utils.py │ └── ultralytics_utils.py ├── notebooks └── quicktour.ipynb ├── poetry.lock ├── pyproject.toml └── tests └── __init__.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | *.DS_Store 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/README.md -------------------------------------------------------------------------------- /clearedge/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /clearedge/bbox.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/bbox.py -------------------------------------------------------------------------------- /clearedge/chunk.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/chunk.py -------------------------------------------------------------------------------- /clearedge/metadata.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/metadata.py -------------------------------------------------------------------------------- /clearedge/ocr_config/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/ocr_config/config.yaml -------------------------------------------------------------------------------- /clearedge/reader/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/reader/__init__.py -------------------------------------------------------------------------------- /clearedge/reader/en_PP-OCRv4_rec_infer.onnx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/reader/en_PP-OCRv4_rec_infer.onnx -------------------------------------------------------------------------------- /clearedge/reader/pdf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/reader/pdf.py -------------------------------------------------------------------------------- /clearedge/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /clearedge/utils/hf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/utils/hf_utils.py -------------------------------------------------------------------------------- /clearedge/utils/pdf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/utils/pdf_utils.py -------------------------------------------------------------------------------- /clearedge/utils/ultralytics_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/clearedge/utils/ultralytics_utils.py -------------------------------------------------------------------------------- /notebooks/quicktour.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/notebooks/quicktour.ipynb -------------------------------------------------------------------------------- /poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/poetry.lock -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Clearedge-AI/clearedge/HEAD/pyproject.toml -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | --------------------------------------------------------------------------------