|
|
|
from .gmft import convert_gmft |
|
from .pypdf import convert_pypdf |
|
from .smoldocling import convert_smoldocling |
|
from .unstructured import convert_unstructured |
|
|
|
__all__ = [ |
|
"convert_smoldocling", |
|
"convert_unstructured", |
|
"convert_gmft", |
|
"convert_pypdf", |
|
] |
|
|
|
SUPPORTED_METHODS = [ |
|
"SmolDocling", |
|
"PyMuPDF", |
|
"PyPDF", |
|
"Unstructured", |
|
"GMFT (table-only)", |
|
] |
|
SUPPORTED_METHODS_METADATA = { |
|
"Unstructured": { |
|
"name": "Unstructured", |
|
"description": "Open-Source Pre-Processing Tools for Unstructured Data.", |
|
"url": "https://github.com/Unstructured-IO/unstructured", |
|
"documentation": "https://docs.unstructured.io/welcome", |
|
}, |
|
"Marker": { |
|
"name": "Marker", |
|
"description": "Marker converts documents to markdown, JSON, and HTML quickly and accurately.", |
|
"url": "https://github.com/VikParuchuri/marker", |
|
"documentation": "https://github.com/VikParuchuri/marker", |
|
}, |
|
"MinerU": { |
|
"name": "MinerU", |
|
"description": "A high-quality tool for convert PDF to Markdown and JSON.", |
|
"url": "https://github.com/opendatalab/MinerU", |
|
"documentation": "https://github.com/opendatalab/MinerU", |
|
}, |
|
"Docling": { |
|
"name": "Docling", |
|
"description": "Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.", |
|
"url": "https://github.com/DS4SD/docling", |
|
"documentation": "https://ds4sd.github.io/docling/", |
|
}, |
|
"SmolDocling": { |
|
"name": "SmolDocling", |
|
"description": "SmolDocling is a multimodal Image-Text-to-Text model designed for efficient document conversion. It retains Docling's most popular features while ensuring full compatibility with Docling through seamless support for DoclingDocuments.", |
|
"url": "https://huggingface.co/ds4sd/SmolDocling-256M-preview", |
|
"documentation": "https://huggingface.co/ds4sd/SmolDocling-256M-preview", |
|
}, |
|
"PyMuPDF": { |
|
"name": "PyMuPDF", |
|
"description": "PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.", |
|
"url": "https://github.com/pymupdf/PyMuPDF", |
|
"documentation": "https://pymupdf.readthedocs.io/en/latest/pymupdf4llm/index.html", |
|
}, |
|
"Gemini (API)": { |
|
"name": "Gemini", |
|
"description": "Using Gemini multimodal API to parse PDF to markdown.", |
|
"url": None, |
|
"documentation": "https://ai.google.dev/gemini-api/docs/document-processing?lang=python", |
|
}, |
|
"Img2Table (table-only)": { |
|
"name": "Img2Table", |
|
"description": "img2table is a table identification and extraction Python Library for PDF and images, based on OpenCV image processing.", |
|
"url": "https://github.com/xavctn/img2table", |
|
"documentation": "https://github.com/xavctn/img2table", |
|
}, |
|
"GMFT (table-only)": { |
|
"name": "GMFT", |
|
"description": "Lightweight, performant, deep table extraction.", |
|
"url": "https://github.com/conjuncts/gmft", |
|
"documentation": "https://github.com/conjuncts/gmft", |
|
}, |
|
"Sycamore": { |
|
"name": "Sycamore", |
|
"description": "Sycamore is an open source, AI-powered document processing engine for ETL, RAG, LLM-based applications, and analytics on unstructured data.", |
|
"url": "https://github.com/aryn-ai/sycamore", |
|
"documentation": "https://sycamore.readthedocs.io/en/stable/", |
|
}, |
|
"PyPDF": { |
|
"name": "PyPDF", |
|
"description": "PyPDF is a pure-Python PDF toolkit that can help you read, write, and manipulate PDF documents.", |
|
"url": "https://github.com/py-pdf/pypdf", |
|
"documentation": "https://pypdf.readthedocs.io/en/stable", |
|
}, |
|
} |
|
|
