├── .gitignore ├── CHANGES.md ├── LICENSE ├── README.md ├── examples ├── GUI │ ├── README.md │ └── browser-app.py ├── README.md └── country-capitals │ ├── README.md │ ├── country-capitals.py │ └── national-capitals.pdf ├── pdf4llm ├── LICENSE ├── README.md ├── pdf4llm │ └── __init__.py └── setup.py ├── pymupdf4llm ├── LICENSE ├── README.md ├── pymupdf4llm │ ├── __init__.py │ ├── helpers │ │ ├── check_ocr.py │ │ ├── document_layout.py │ │ ├── get_text_lines.py │ │ ├── multi_column.py │ │ ├── progress.py │ │ ├── pymupdf_rag.py │ │ └── utils.py │ ├── llama │ │ └── pdf_markdown_reader.py │ └── versions_file.py └── setup.py └── tests └── pymupdf4llm └── llama_index └── test_pdf_markdown_reader.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/.gitignore -------------------------------------------------------------------------------- /CHANGES.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/CHANGES.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/README.md -------------------------------------------------------------------------------- /examples/GUI/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/GUI/README.md -------------------------------------------------------------------------------- /examples/GUI/browser-app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/GUI/browser-app.py -------------------------------------------------------------------------------- /examples/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/README.md -------------------------------------------------------------------------------- /examples/country-capitals/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/country-capitals/README.md -------------------------------------------------------------------------------- /examples/country-capitals/country-capitals.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/country-capitals/country-capitals.py -------------------------------------------------------------------------------- /examples/country-capitals/national-capitals.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/examples/country-capitals/national-capitals.pdf -------------------------------------------------------------------------------- /pdf4llm/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pdf4llm/LICENSE -------------------------------------------------------------------------------- /pdf4llm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pdf4llm/README.md -------------------------------------------------------------------------------- /pdf4llm/pdf4llm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pdf4llm/pdf4llm/__init__.py -------------------------------------------------------------------------------- /pdf4llm/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pdf4llm/setup.py -------------------------------------------------------------------------------- /pymupdf4llm/LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/LICENSE -------------------------------------------------------------------------------- /pymupdf4llm/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/README.md -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/__init__.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/check_ocr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/check_ocr.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/document_layout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/document_layout.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/get_text_lines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/get_text_lines.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/multi_column.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/multi_column.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/progress.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/progress.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/pymupdf_rag.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/pymupdf_rag.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/helpers/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/helpers/utils.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/llama/pdf_markdown_reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/llama/pdf_markdown_reader.py -------------------------------------------------------------------------------- /pymupdf4llm/pymupdf4llm/versions_file.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/pymupdf4llm/versions_file.py -------------------------------------------------------------------------------- /pymupdf4llm/setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/pymupdf4llm/setup.py -------------------------------------------------------------------------------- /tests/pymupdf4llm/llama_index/test_pdf_markdown_reader.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/pymupdf/pymupdf4llm/HEAD/tests/pymupdf4llm/llama_index/test_pdf_markdown_reader.py --------------------------------------------------------------------------------