Skip to content

GitLab

"comfy/vscode:/vscode.git/clone" did not exist on "0ed72befe18e086ac160f1a55aa69b37c928ebb9"
Unverified Commit 6ab12348 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #2625 from opendatalab/release-2.0.0 

Release 2.0.0
parents 9487d33d 4fbec469
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 1865 deletions
next_docs/en/api/pipe_operators.rst deleted 100644 → 0
View file @ 9487d33d
Pipeline Api
=============
.. autoclass:: magic_pdf.operators.pipes.PipeResult
:members:
:inherited-members:
:show-inheritance:
next_docs/en/api/read_api.rst deleted 100644 → 0
View file @ 9487d33d
read_api
=========
.. automodule:: magic_pdf.data.read_api
:members:
:inherited-members:
next_docs/en/api/schemas.rst deleted 100644 → 0
View file @ 9487d33d
schemas
===========
.. autopydantic_model:: magic_pdf.data.schemas.S3Config
:members:
.. autopydantic_model:: magic_pdf.data.schemas.PageInfo
:members:
next_docs/en/conf.py deleted 100644 → 0
View file @ 9487d33d
# Configuration file for the Sphinx documentation builder.
#
# This file only contains a selection of the most common options. For a full
# list see the documentation:
# https://www.sphinx-doc.org/en/master/usage/configuration.html
# -- Path setup --------------------------------------------------------------
# If extensions (or modules to document with autodoc) are in another directory,
# add these directories to sys.path here. If the directory is relative to the
# documentation root, use os.path.abspath to make it absolute, like shown here.
import os
import subprocess
import sys
from sphinx.ext import autodoc
from docutils import nodes
from docutils.parsers.rst import Directive
def install(package):
subprocess.check_call([sys.executable, '-m', 'pip', 'install', package])
requirements_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'requirements.txt'))
if os.path.exists(requirements_path):
with open(requirements_path) as f:
packages = f.readlines()
for package in packages:
install(package.strip())
sys.path.insert(0, os.path.abspath('../..'))
# -- Project information -----------------------------------------------------
project = 'MinerU'
copyright = '2024, MinerU Contributors'
author = 'OpenDataLab'
# The full version, including alpha/beta/rc tags
version_file = '../../magic_pdf/libs/version.py'
with open(version_file) as f:
exec(compile(f.read(), version_file, 'exec'))
__version__ = locals()['__version__']
# The short X.Y version
version = __version__
# The full version, including alpha/beta/rc tags
release = __version__
# -- General configuration ---------------------------------------------------
# Add any Sphinx extension module names here, as strings. They can be
# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
# ones.
extensions = [
'sphinx.ext.napoleon',
'sphinx.ext.viewcode',
'sphinx.ext.intersphinx',
'sphinx_copybutton',
'sphinx.ext.autodoc',
'sphinx.ext.autosummary',
'sphinx.ext.inheritance_diagram',
'myst_parser',
'sphinxarg.ext',
'sphinxcontrib.autodoc_pydantic',
]
# class hierarchy diagram
inheritance_graph_attrs = dict(rankdir="LR", size='"8.0, 12.0"', fontsize=14, ratio='compress')
inheritance_node_attrs = dict(shape='ellipse', fontsize=14, height=0.75)
inheritance_edge_attrs = dict(arrow='vee')
autodoc_pydantic_model_show_json = True
autodoc_pydantic_model_show_config_summary = False
# Add any paths that contain templates here, relative to this directory.
templates_path = ['_templates']
# List of patterns, relative to source directory, that match files and
# directories to ignore when looking for source files.
# This pattern also affects html_static_path and html_extra_path.
exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
# Exclude the prompt "$" when copying code
copybutton_prompt_text = r'\$ '
copybutton_prompt_is_regexp = True
language = 'en'
# -- Options for HTML output -------------------------------------------------
# The theme to use for HTML and HTML Help pages. See the documentation for
# a list of builtin themes.
#
html_theme = 'sphinx_book_theme'
html_logo = '_static/image/logo.png'
html_theme_options = {
'path_to_docs': 'next_docs/en',
'repository_url': 'https://github.com/opendatalab/MinerU',
'use_repository_button': True,
}
# Add any paths that contain custom static files (such as style sheets) here,
# relative to this directory. They are copied after the builtin static files,
# so a file named "default.css" will overwrite the builtin "default.css".
# html_static_path = ['_static']
# Mock out external dependencies here.
autodoc_mock_imports = [
'cpuinfo',
'torch',
'transformers',
'psutil',
'prometheus_client',
'sentencepiece',
'vllm.cuda_utils',
'vllm._C',
# 'numpy',
'tqdm',
]
class MockedClassDocumenter(autodoc.ClassDocumenter):
"""Remove note about base class when a class is derived from object."""
def add_line(self, line: str, source: str, *lineno: int) -> None:
if line == ' Bases: :py:class:`object`':
return
super().add_line(line, source, *lineno)
autodoc.ClassDocumenter = MockedClassDocumenter
navigation_with_keys = False
# add custom directive
class VideoDirective(Directive):
required_arguments = 1
optional_arguments = 0
final_argument_whitespace = True
option_spec = {}
def run(self):
url = self.arguments[0]
video_node = nodes.raw('', f'<iframe width="560" height="315" src="{url}" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>', format='html')
return [video_node]
def setup(app):
app.add_directive('video', VideoDirective)
\ No newline at end of file
next_docs/en/index.rst deleted 100644 → 0
View file @ 9487d33d
.. xtuner documentation master file, created by
sphinx-quickstart on Tue Jan 9 16:33:06 2024.
You can adapt this file completely to your liking, but it should at least
contain the root `toctree` directive.
Welcome to the MinerU Documentation
==============================================
.. figure:: ./_static/image/logo.png
:align: center
:alt: mineru
:class: no-scaled-link
.. raw:: html
<p style="text-align:center">
<strong>A one-stop, open-source, high-quality data extraction tool
</strong>
</p>
<p style="text-align:center">
<script async defer src="https://buttons.github.io/buttons.js"></script>
<a class="github-button" href="https://github.com/opendatalab/MinerU" data-show-count="true" data-size="large" aria-label="Star">Star</a>
<a class="github-button" href="https://github.com/opendatalab/MinerU/subscription" data-icon="octicon-eye" data-size="large" aria-label="Watch">Watch</a>
<a class="github-button" href="https://github.com/opendatalab/MinerU/fork" data-icon="octicon-repo-forked" data-size="large" aria-label="Fork">Fork</a>
</p>
Project Introduction
--------------------
MinerU is a tool that converts PDFs into machine-readable formats (e.g.,
markdown, JSON), allowing for easy extraction into any format. MinerU
was born during the pre-training process of
`InternLM <https://github.com/InternLM/InternLM>`__. We focus on solving
symbol conversion issues in scientific literature and hope to contribute
to technological development in the era of large models. Compared to
well-known commercial products, MinerU is still young. If you encounter
any issues or if the results are not as expected, please submit an issue
on `issue <https://github.com/opendatalab/MinerU/issues>`__ and **attach
the relevant PDF**.
.. video:: https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
Key Features
------------
- Remove headers, footers, footnotes, page numbers, etc., to ensure
semantic coherence.
- Output text in human-readable order, suitable for single-column,
multi-column, and complex layouts.
- Preserve the structure of the original document, including headings,
paragraphs, lists, etc.
- Extract images, image descriptions, tables, table titles, and
footnotes.
- Automatically recognize and convert formulas in the document to LaTeX
format.
- Automatically recognize and convert tables in the document to LaTeX
or HTML format.
- Automatically detect scanned PDFs and garbled PDFs and enable OCR
functionality.
- OCR supports detection and recognition of 84 languages.
- Supports multiple output formats, such as multimodal and NLP
Markdown, JSON sorted by reading order, and rich intermediate
formats.
- Supports various visualization results, including layout
visualization and span visualization, for efficient confirmation of
output quality.
- Supports both CPU and GPU environments.
- Compatible with Windows, Linux, and Mac platforms.
.. tip::
Get started with MinerU by trying the `online demo <https://www.modelscope.cn/studios/OpenDataLab/MinerU>`_ or :doc:`installing it locally <user_guide/install/install>`.
User Guide
-------------
.. toctree::
:maxdepth: 2
:caption: User Guide
user_guide
API Reference
-------------
If you are looking for information on a specific function, class or
method, this part of the documentation is for you.
.. toctree::
:maxdepth: 2
:caption: API
api
Additional Notes
------------------
.. toctree::
:maxdepth: 1
:caption: Additional Notes
additional_notes/known_issues
additional_notes/faq
additional_notes/glossary
next_docs/en/make.bat deleted 100644 → 0
View file @ 9487d33d
@ECHO OFF
pushd %~dp0
REM Command file for Sphinx documentation
if "%SPHINXBUILD%" == "" (
set SPHINXBUILD=sphinx-build
)
set SOURCEDIR=.
set BUILDDIR=_build
%SPHINXBUILD% >NUL 2>NUL
if errorlevel 9009 (
echo.
echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
echo.installed, then set the SPHINXBUILD environment variable to point
echo.to the full path of the 'sphinx-build' executable. Alternatively you
echo.may add the Sphinx directory to PATH.
echo.
echo.If you don't have Sphinx installed, grab it from
echo.https://www.sphinx-doc.org/
exit /b 1
)
if "%1" == "" goto help
%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
goto end
:help
%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
:end
popd
next_docs/en/user_guide.rst deleted 100644 → 0
View file @ 9487d33d
.. toctree::
:maxdepth: 2
user_guide/install
user_guide/usage
user_guide/quick_start
user_guide/tutorial
user_guide/data
user_guide/inference_result
user_guide/pipe_result
next_docs/en/user_guide/data.rst deleted 100644 → 0
View file @ 9487d33d
Data
=========
.. toctree::
:maxdepth: 2
data/dataset
data/read_api
data/data_reader_writer
data/io
next_docs/en/user_guide/data/data_reader_writer.rst deleted 100644 → 0
View file @ 9487d33d
Data Reader Writer
====================
Aims for read or write bytes from different media, You can implement new classes to meet the needs of your personal scenarios
if MinerU have not provide the suitable classes. It is easy to implement new classes, the only one requirement is to inherit from
``DataReader`` or ``DataWriter``
.. code:: python
class SomeReader(DataReader):
def read(self, path: str) -> bytes:
pass
def read_at(self, path: str, offset: int = 0, limit: int = -1) -> bytes:
pass
class SomeWriter(DataWriter):
def write(self, path: str, data: bytes) -> None:
pass
def write_string(self, path: str, data: str) -> None:
pass
Reader may curious about the difference between :doc:`io` and this section. Those two sections look very similarity at first glance.
:doc:`io` provides fundamental functions, while This section thinks more at application level. Customer can build they own classes to meet
their own applications need which may share same IO function. That is why we have :doc:`io`.
Important Classes
-----------------
.. code:: python
class FileBasedDataReader(DataReader):
def __init__(self, parent_dir: str = ''):
pass
class FileBasedDataWriter(DataWriter):
def __init__(self, parent_dir: str = '') -> None:
pass
Class ``FileBasedDataReader`` initialized with unary param ``parent_dir``, That means that every method ``FileBasedDataReader`` provided will have features as follow.
Features:
#. read content from the absolute path file, ``parent_dir`` will be ignored.
#. read the relative path, file will first join with ``parent_dir``, then read content from the merged path
.. note::
``FileBasedDataWriter`` shares the same behavior with ``FileBaseDataReader``
.. code:: python
class MultiS3Mixin:
def __init__(self, default_prefix: str, s3_configs: list[S3Config]):
pass
class MultiBucketS3DataReader(DataReader, MultiS3Mixin):
pass
All read-related method that class ``MultiBucketS3DataReader`` provided will have features as follow.
Features:
#. read object with full s3-format path, for example ``s3://test_bucket/test_object``, ``default_prefix`` will be ignored.
#. read object with relative path, file will join ``default_prefix`` and trim the ``bucket_name`` firstly, then read the content. ``bucket_name`` is the first element of the result after split ``default_prefix`` with delimiter ``\``
.. note::
``MultiBucketS3DataWriter`` shares the same behavior with ``MultiBucketS3DataReader``
.. code:: python
class S3DataReader(MultiBucketS3DataReader):
pass
``S3DataReader`` is build on top of MultiBucketS3DataReader which only support for bucket. So is ``S3DataWriter``.
Read Examples
------------
.. code:: python
import os
from magic_pdf.data.data_reader_writer import *
from magic_pdf.data.data_reader_writer import MultiBucketS3DataReader
from magic_pdf.data.schemas import S3Config
# file based related
file_based_reader1 = FileBasedDataReader('')
## will read file abc
file_based_reader1.read('abc')
file_based_reader2 = FileBasedDataReader('/tmp')
## will read /tmp/abc
file_based_reader2.read('abc')
## will read /tmp/logs/message.txt
file_based_reader2.read('/tmp/logs/message.txt')
# multi bucket s3 releated
bucket = "bucket" # replace with real bucket
ak = "ak" # replace with real access key
sk = "sk" # replace with real secret key
endpoint_url = "endpoint_url" # replace with real endpoint_url
bucket_2 = "bucket_2" # replace with real bucket
ak_2 = "ak_2" # replace with real access key
sk_2 = "sk_2" # replace with real secret key
endpoint_url_2 = "endpoint_url_2" # replace with real endpoint_url
test_prefix = 'test/unittest'
multi_bucket_s3_reader1 = MultiBucketS3DataReader(f"{bucket}/{test_prefix}", [S3Config(
bucket_name=bucket, access_key=ak, secret_key=sk, endpoint_url=endpoint_url
),
S3Config(
bucket_name=bucket_2,
access_key=ak_2,
secret_key=sk_2,
endpoint_url=endpoint_url_2,
)])
## will read s3://{bucket}/{test_prefix}/abc
multi_bucket_s3_reader1.read('abc')
## will read s3://{bucket}/{test_prefix}/efg
multi_bucket_s3_reader1.read(f's3://{bucket}/{test_prefix}/efg')
## will read s3://{bucket2}/{test_prefix}/abc
multi_bucket_s3_reader1.read(f's3://{bucket_2}/{test_prefix}/abc')
# s3 related
s3_reader1 = S3DataReader(
test_prefix,
bucket,
ak,
sk,
endpoint_url
)
## will read s3://{bucket}/{test_prefix}/abc
s3_reader1.read('abc')
## will read s3://{bucket}/efg
s3_reader1.read(f's3://{bucket}/efg')
Write Examples
---------------
.. code:: python
import os
from magic_pdf.data.data_reader_writer import *
from magic_pdf.data.data_reader_writer import MultiBucketS3DataWriter
from magic_pdf.data.schemas import S3Config
# file based related
file_based_writer1 = FileBasedDataWriter("")
## will write 123 to abc
file_based_writer1.write("abc", "123".encode())
## will write 123 to abc
file_based_writer1.write_string("abc", "123")
file_based_writer2 = FileBasedDataWriter("/tmp")
## will write 123 to /tmp/abc
file_based_writer2.write_string("abc", "123")
## will write 123 to /tmp/logs/message.txt
file_based_writer2.write_string("/tmp/logs/message.txt", "123")
# multi bucket s3 releated
bucket = "bucket" # replace with real bucket
ak = "ak" # replace with real access key
sk = "sk" # replace with real secret key
endpoint_url = "endpoint_url" # replace with real endpoint_url
bucket_2 = "bucket_2" # replace with real bucket
ak_2 = "ak_2" # replace with real access key
sk_2 = "sk_2" # replace with real secret key
endpoint_url_2 = "endpoint_url_2" # replace with real endpoint_url
test_prefix = "test/unittest"
multi_bucket_s3_writer1 = MultiBucketS3DataWriter(
f"{bucket}/{test_prefix}",
[
S3Config(
bucket_name=bucket, access_key=ak, secret_key=sk, endpoint_url=endpoint_url
),
S3Config(
bucket_name=bucket_2,
access_key=ak_2,
secret_key=sk_2,
endpoint_url=endpoint_url_2,
),
],
)
## will write 123 to s3://{bucket}/{test_prefix}/abc
multi_bucket_s3_writer1.write_string("abc", "123")
## will write 123 to s3://{bucket}/{test_prefix}/abc
multi_bucket_s3_writer1.write("abc", "123".encode())
## will write 123 to s3://{bucket}/{test_prefix}/efg
multi_bucket_s3_writer1.write(f"s3://{bucket}/{test_prefix}/efg", "123".encode())
## will write 123 to s3://{bucket_2}/{test_prefix}/abc
multi_bucket_s3_writer1.write(f's3://{bucket_2}/{test_prefix}/abc', '123'.encode())
# s3 related
s3_writer1 = S3DataWriter(test_prefix, bucket, ak, sk, endpoint_url)
## will write 123 to s3://{bucket}/{test_prefix}/abc
s3_writer1.write("abc", "123".encode())
## will write 123 to s3://{bucket}/{test_prefix}/abc
s3_writer1.write_string("abc", "123")
## will write 123 to s3://{bucket}/efg
s3_writer1.write(f"s3://{bucket}/efg", "123".encode())
Check :doc:`../../api/data_reader_writer` for more details
next_docs/en/user_guide/data/dataset.rst deleted 100644 → 0
View file @ 9487d33d
Dataset
===========
Import Classes
-----------------
Dataset
^^^^^^^^
Each pdfs or image will form one ``Dataset``. As we all know, Pdf has two categories, :ref:`digital_method_section` or :ref:`ocr_method_section`.
Will get ``ImageDataset`` which is subclass of ``Dataset`` with images and get ``PymuDocDataset`` from pdf files.
The difference between ``ImageDataset`` and ``PymuDocDataset`` is that ``ImageDataset`` only support ``OCR`` parse method,
while ``PymuDocDataset`` support both ``OCR`` and ``TXT``
.. note::
In fact some pdf may generated by images, that means it can not support ``TXT`` methods. Currently it is something the user needs to ensure does not happen
Pdf Parse Methods
------------------
.. _ocr_method_section:
OCR
^^^^
Extract chars via ``Optical Character Recognition`` technical.
.. _digital_method_section:
TXT
^^^^^^^^
Extract chars via third-party library, currently we use ``pymupdf``.
Check :doc:`../../api/dataset` for more details
next_docs/en/user_guide/data/io.rst deleted 100644 → 0
View file @ 9487d33d
IO
===
Aims for read or write bytes from different media, Currently We provide ``S3Reader``, ``S3Writer`` for AWS S3 compatible media
and ``HttpReader``, ``HttpWriter`` for remote Http file. You can implement new classes to meet the needs of your personal scenarios
if MinerU have not provide the suitable classes. It is easy to implement new classes, the only one requirement is to inherit from
``IOReader`` or ``IOWriter``
.. code:: python
class SomeReader(IOReader):
def read(self, path: str) -> bytes:
pass
def read_at(self, path: str, offset: int = 0, limit: int = -1) -> bytes:
pass
class SomeWriter(IOWriter):
def write(self, path: str, data: bytes) -> None:
pass
Check :doc:`../../api/io` for more details
next_docs/en/user_guide/data/read_api.rst deleted 100644 → 0
View file @ 9487d33d
read_api
==========
Read the content from file or directory to create ``Dataset``, Currently we provided serval functions that cover some scenarios.
if you have new scenarios that is common to most of the users, you can post it on the offical github issues with detail descriptions.
Also it is easy to implement your own read-related funtions.
Important Functions
-------------------
read_jsonl
^^^^^^^^^^^^^^^^
Read the contet from jsonl which may located on local machine or remote s3. if you want to know more about jsonl, please goto :doc:`../../additional_notes/glossary`
.. code:: python
from magic_pdf.data.read_api import *
from magic_pdf.data.data_reader_writer import MultiBucketS3DataReader
from magic_pdf.data.schemas import S3Config
# read jsonl from local machine
datasets = read_jsonl("tt.jsonl", None) # replace with real jsonl file
# read jsonl from remote s3
bucket = "bucket_1" # replace with real s3 bucket
ak = "access_key_1" # replace with real s3 access key
sk = "secret_key_1" # replace with real s3 secret key
endpoint_url = "endpoint_url_1" # replace with real s3 endpoint url
bucket_2 = "bucket_2" # replace with real s3 bucket
ak_2 = "access_key_2" # replace with real s3 access key
sk_2 = "secret_key_2" # replace with real s3 secret key
endpoint_url_2 = "endpoint_url_2" # replace with real s3 endpoint url
s3configs = [
S3Config(
bucket_name=bucket, access_key=ak, secret_key=sk, endpoint_url=endpoint_url
),
S3Config(
bucket_name=bucket_2,
access_key=ak_2,
secret_key=sk_2,
endpoint_url=endpoint_url_2,
),
]
s3_reader = MultiBucketS3DataReader(bucket, s3configs)
datasets = read_jsonl(f"s3://bucket_1/tt.jsonl", s3_reader) # replace with real s3 jsonl file
read_local_pdfs
^^^^^^^^^^^^^^^^^
Read pdf from path or directory.
.. code:: python
from magic_pdf.data.read_api import *
# read pdf path
datasets = read_local_pdfs("tt.pdf")
# read pdfs under directory
datasets = read_local_pdfs("pdfs/")
read_local_images
^^^^^^^^^^^^^^^^^^^
Read images from path or directory
.. code:: python
from magic_pdf.data.read_api import *
# read from image path
datasets = read_local_images("tt.png") # replace with real file path
# read files from directory that endswith suffix in suffixes array
datasets = read_local_images("images/", suffixes=[".png", ".jpg"]) # replace with real directory
read_local_office
^^^^^^^^^^^^^^^^^^^^
Read MS-Office files from path or directory
.. code:: python
from magic_pdf.data.read_api import *
# read from image path
datasets = read_local_office("tt.doc") # replace with real file path
# read files from directory that endswith suffix in suffixes array
datasets = read_local_office("docs/") # replace with real directory
Check :doc:`../../api/read_api` for more details
\ No newline at end of file
next_docs/en/user_guide/inference_result.rst deleted 100644 → 0
View file @ 9487d33d
Inference Result
==================
.. admonition:: Tip
:class: tip
Please first navigate to :doc:`tutorial/pipeline` to get an initial understanding of how the pipeline works; this will help in understanding the content of this section.
The **InferenceResult** class is a container for storing model inference results and implements a series of methods related to these results, such as draw_model, dump_model.
Checkout :doc:`../api/model_operators` for more details about **InferenceResult**
Model Inference Result
-----------------------
Structure Definition
^^^^^^^^^^^^^^^^^^^^^^^^
.. code:: python
from pydantic import BaseModel, Field
from enum import IntEnum
class CategoryType(IntEnum):
title = 0 # Title
plain_text = 1 # Text
abandon = 2 # Includes headers, footers, page numbers, and page annotations
figure = 3 # Image
figure_caption = 4 # Image description
table = 5 # Table
table_caption = 6 # Table description
table_footnote = 7 # Table footnote
isolate_formula = 8 # Block formula
formula_caption = 9 # Formula label
embedding = 13 # Inline formula
isolated = 14 # Block formula
text = 15 # OCR recognition result
class PageInfo(BaseModel):
page_no: int = Field(description="Page number, the first page is 0", ge=0)
height: int = Field(description="Page height", gt=0)
width: int = Field(description="Page width", ge=0)
class ObjectInferenceResult(BaseModel):
category_id: CategoryType = Field(description="Category", ge=0)
poly: list[float] = Field(description="Quadrilateral coordinates, representing the coordinates of the top-left, top-right, bottom-right, and bottom-left points respectively")
score: float = Field(description="Confidence of the inference result")
latex: str | None = Field(description="LaTeX parsing result", default=None)
html: str | None = Field(description="HTML parsing result", default=None)
class PageInferenceResults(BaseModel):
layout_dets: list[ObjectInferenceResult] = Field(description="Page recognition results", ge=0)
page_info: PageInfo = Field(description="Page metadata")
Example
^^^^^^^^^^^
.. code:: json
[
{
"layout_dets": [
{
"category_id": 2,
"poly": [
99.1906967163086,
100.3119125366211,
730.3707885742188,
100.3119125366211,
730.3707885742188,
245.81326293945312,
99.1906967163086,
245.81326293945312
],
"score": 0.9999997615814209
}
],
"page_info": {
"page_no": 0,
"height": 2339,
"width": 1654
}
},
{
"layout_dets": [
{
"category_id": 5,
"poly": [
99.13092803955078,
2210.680419921875,
497.3183898925781,
2210.680419921875,
497.3183898925781,
2264.78076171875,
99.13092803955078,
2264.78076171875
],
"score": 0.9999997019767761
}
],
"page_info": {
"page_no": 1,
"height": 2339,
"width": 1654
}
}
]
The format of the poly coordinates is [x0, y0, x1, y1, x2, y2, x3, y3],
representing the coordinates of the top-left, top-right, bottom-right,
and bottom-left points respectively. |Poly Coordinate Diagram|
Inference Result
-------------------------
.. code:: python
from magic_pdf.operators.models import InferenceResult
from magic_pdf.data.dataset import Dataset
dataset : Dataset = some_data_set # not real dataset
# The inference results of all pages, ordered by page number, are stored in a list as the inference results of MinerU
model_inference_result: list[PageInferenceResults] = []
Inference_result = InferenceResult(model_inference_result, dataset)
some_model.pdf
^^^^^^^^^^^^^^^^^^^^
.. figure:: ../_static/image/inference_result.png
.. |Poly Coordinate Diagram| image:: ../_static/image/poly.png
next_docs/en/user_guide/install.rst deleted 100644 → 0
View file @ 9487d33d
Installation
==============
.. toctree::
:maxdepth: 1
install/install
install//boost_with_cuda
install/download_model_weight_files
install/config
next_docs/en/user_guide/install/boost_with_cuda.rst deleted 100644 → 0
View file @ 9487d33d
Boost With Cuda
================
If your device supports CUDA and meets the GPU requirements of the
mainline environment, you can use GPU acceleration. Please select the
appropriate guide based on your system:
- :ref:`ubuntu_22_04_lts_section`
- :ref:`windows_10_or_11_section`
.. _ubuntu_22_04_lts_section:
Ubuntu 22.04 LTS
-----------------
1. Check if NVIDIA Drivers Are Installed
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
.. code:: sh
nvidia-smi
If you see information similar to the following, it means that the
NVIDIA drivers are already installed, and you can skip Step 2.
.. note::
``CUDA Version`` should be >= 12.4, If the displayed version number is less than 12.4, please upgrade the driver.
.. code:: text
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.133.07 Driver Version: 572.83 CUDA Version: 12.8 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 NVIDIA GeForce RTX 3060 Ti WDDM | 00000000:01:00.0 On | N/A |
| 0% 51C P8 12W / 200W | 1489MiB / 8192MiB | 5% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
2. Install the Driver
~~~~~~~~~~~~~~~~~~~~~
If no driver is installed, use the following command:
.. code:: sh
sudo apt-get update
sudo apt-get install nvidia-driver-570-server
Install the proprietary driver and restart your computer after
installation.
.. code:: sh
reboot
3. Install Anaconda
~~~~~~~~~~~~~~~~~~~
If Anaconda is already installed, skip this step.
.. code:: sh
wget https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Linux-x86_64.sh
bash Anaconda3-2024.06-1-Linux-x86_64.sh
In the final step, enter ``yes``, close the terminal, and reopen it.
4. Create an Environment Using Conda
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Specify Python version 3.10～3.13.
.. code:: sh
conda create -n mineru 'python=3.12' -y
conda activate mineru
5. Install Applications
~~~~~~~~~~~~~~~~~~~~~~~
.. code:: sh
pip install -U magic-pdf[full]
.. admonition:: TIP
:class: tip
After installation, you can check the version of ``magic-pdf`` using the following command:
.. code:: sh
magic-pdf --version
6. Download Models
~~~~~~~~~~~~~~~~~~
Refer to detailed instructions on :doc:`download_model_weight_files`
7. Understand the Location of the Configuration File
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
After completing the `6. Download Models <#6-download-models>`__ step,
the script will automatically generate a ``magic-pdf.json`` file in the
user directory and configure the default model path. You can find the
``magic-pdf.json`` file in your user directory.
.. admonition:: TIP
:class: tip
The user directory for Linux is “/home/username”.
8. First Run
~~~~~~~~~~~~
Download a sample file from the repository and test it.
.. code:: sh
wget https://github.com/opendatalab/MinerU/raw/master/demo/pdfs/small_ocr.pdf
magic-pdf -p small_ocr.pdf -o ./output
9. Test CUDA Acceleration
~~~~~~~~~~~~~~~~~~~~~~~~~
If your graphics card has at least **8GB** of VRAM, follow these steps
to test CUDA acceleration:
1. Modify the value of ``"device-mode"`` in the ``magic-pdf.json``
configuration file located in your home directory.
.. code:: json
{
"device-mode": "cuda"
}
2. Test CUDA acceleration with the following command:
.. code:: sh
magic-pdf -p small_ocr.pdf -o ./output
.. _windows_10_or_11_section:
Windows 10/11
--------------
1. Install CUDA
~~~~~~~~~~~~~~~~~~~~~~~~~
You need to install a CUDA version that is compatible with torch's requirements. For details, please refer to the [official PyTorch website](https://pytorch.org/get-started/locally/).
- CUDA 11.8 https://developer.nvidia.com/cuda-11-8-0-download-archive
- CUDA 12.4 https://developer.nvidia.com/cuda-12-4-0-download-archive
- CUDA 12.6 https://developer.nvidia.com/cuda-12-6-0-download-archive
- CUDA 12.8 https://developer.nvidia.com/cuda-12-8-0-download-archive
2. Install Anaconda
~~~~~~~~~~~~~~~~~~~
If Anaconda is already installed, you can skip this step.
Download link: https://repo.anaconda.com/archive/Anaconda3-2024.06-1-Windows-x86_64.exe
3. Create an Environment Using Conda
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
::
conda create -n mineru 'python=3.12' -y
conda activate mineru
4. Install Applications
~~~~~~~~~~~~~~~~~~~~~~~
::
pip install -U magic-pdf[full]
.. admonition:: Tip
:class: tip
After installation, you can check the version of ``magic-pdf``:
.. code:: bash
magic-pdf --version
5. Download Models
~~~~~~~~~~~~~~~~~~
Refer to detailed instructions on :doc:`download_model_weight_files`
6. Understand the Location of the Configuration File
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
After completing the `5. Download Models <#5-download-models>`__ step,
the script will automatically generate a ``magic-pdf.json`` file in the
user directory and configure the default model path. You can find the
``magic-pdf.json`` file in your 【user directory】 .
.. admonition:: Tip
:class: tip
The user directory for Windows is “C:/Users/username”.
7. First Run
~~~~~~~~~~~~
Download a sample file from the repository and test it.
.. code:: powershell
wget https://github.com/opendatalab/MinerU/raw/master/demo/pdfs/small_ocr.pdf -O small_ocr.pdf
magic-pdf -p small_ocr.pdf -o ./output
8. Test CUDA Acceleration
~~~~~~~~~~~~~~~~~~~~~~~~~
If your graphics card has at least 8GB of VRAM, follow these steps to
test CUDA-accelerated parsing performance.
1. **Overwrite the installation of torch and torchvision** supporting CUDA.(Please select the appropriate index-url based on your CUDA version. For more details, refer to the [PyTorch official website](https://pytorch.org/get-started/locally/).)
.. code:: sh
pip install --force-reinstall torch torchvision --index-url https://download.pytorch.org/whl/cu124
2. **Modify the value of ``"device-mode"``** in the ``magic-pdf.json``
configuration file located in your user directory.
.. code:: json
{
"device-mode": "cuda"
}
3. **Run the following command to test CUDA acceleration**:
::
magic-pdf -p small_ocr.pdf -o ./output
next_docs/en/user_guide/install/config.rst deleted 100644 → 0
View file @ 9487d33d
Config
=========
File **magic-pdf.json** is typically located in the **${HOME}** directory under a Linux system or in the **C:\Users\{username}** directory under a Windows system.
.. admonition:: Tip
:class: tip
You can override the default location of config file via the following command:
export MINERU_TOOLS_CONFIG_JSON=new_magic_pdf.json
magic-pdf.json
----------------
.. code:: json
{
"bucket_info":{
"bucket-name-1":["ak", "sk", "endpoint"],
"bucket-name-2":["ak", "sk", "endpoint"]
},
"models-dir":"/tmp/models",
"layoutreader-model-dir":"/tmp/layoutreader",
"device-mode":"cpu",
"layout-config": {
"model": "doclayout_yolo"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true
},
"table-config": {
"model": "rapid_table",
"enable": true,
"max_time": 400
},
"config_version": "1.0.0"
}
bucket_info
^^^^^^^^^^^^^^
Store the access_key, secret_key and endpoint of AWS S3 Compatible storage config
Example:
.. code:: text
{
"image_bucket":[{access_key}, {secret_key}, {endpoint}],
"video_bucket":[{access_key}, {secret_key}, {endpoint}]
}
models-dir
^^^^^^^^^^^^
Store the models download from **huggingface** or **modelshop**. You do not need to modify this field if you download the model using the scripts shipped with **MinerU**
layoutreader-model-dir
^^^^^^^^^^^^^^^^^^^^^^^
Store the models download from **huggingface** or **modelshop**. You do not need to modify this field if you download the model using the scripts shipped with **MinerU**
devide-mode
^^^^^^^^^^^^^^
This field have two options, **cpu** or **cuda**.
**cpu**: inference via cpu
**cuda**: using cuda to accelerate inference
layout-config
^^^^^^^^^^^^^^^
.. code:: json
{
"model": "doclayout_yolo"
}
layout model can not be disabled now.
formula-config
^^^^^^^^^^^^^^^^
.. code:: json
{
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true
}
mfd_model
""""""""""
Specify the formula detection model, options are ['yolo_v8_mfd']
mfr_model
""""""""""
Specify the formula recognition model, options are ['unimernet_small']
Check `UniMERNet <https://github.com/opendatalab/UniMERNet>`_ for more details
enable
""""""""
on-off flag, options are [true, false]. **true** means enable formula inference, **false** means disable formula inference
table-config
^^^^^^^^^^^^^^^^
.. code:: json
{
"model": "rapid_table",
"enable": true,
"max_time": 400
}
model
""""""""
Specify the table inference model, options are ['rapid_table']
max_time
"""""""""
Since table recognition is a time-consuming process, we set a timeout period. If the process exceeds this time, the table recognition will be terminated.
enable
"""""""
on-off flag, options are [true, false]. **true** means enable table inference, **false** means disable table inference
config_version
^^^^^^^^^^^^^^^^
The version of config schema.
.. admonition:: Tip
:class: tip
Check `Config Schema <https://github.com/opendatalab/MinerU/blob/master/magic-pdf.template.json>`_ for the latest details
next_docs/en/user_guide/install/download_model_weight_files.rst deleted 100644 → 0
View file @ 9487d33d
Download Model Weight Files
==============================
Model downloads are divided into initial downloads and updates to the
model directory. Please refer to the corresponding documentation for
instructions on how to proceed.
Initial download of model files
------------------------------
1. Download the Model from Hugging Face
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Use a Python Script to Download Model Files from Hugging Face
.. code:: bash
pip install huggingface_hub
wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
python download_models_hf.py
The Python script will automatically download the model files and
configure the model directory in the configuration file.
The configuration file can be found in the user directory, with the
filename ``magic-pdf.json``.
How to update models previously downloaded
-----------------------------------------
1. Models downloaded via Hugging Face or Model Scope
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If you previously downloaded models via Hugging Face or Model Scope, you
can rerun the Python script used for the initial download. This will
automatically update the model directory to the latest version.
next_docs/en/user_guide/install/install.rst deleted 100644 → 0
View file @ 9487d33d
Install
===============================================================
If you encounter any installation issues, please first consult the :doc:`../../additional_notes/faq`.
If the parsing results are not as expected, refer to the :doc:`../../additional_notes/known_issues`.
Also you can try `online demo <https://www.modelscope.cn/studios/OpenDataLab/MinerU>`_ without installation.
.. admonition:: Warning
:class: tip
**Pre-installation Notice—Hardware and Software Environment Support**
To ensure the stability and reliability of the project, we only optimize
and test for specific hardware and software environments during
development. This ensures that users deploying and running the project
on recommended system configurations will get the best performance with
the fewest compatibility issues.
By focusing resources on the mainline environment, our team can more
efficiently resolve potential bugs and develop new features.
In non-mainline environments, due to the diversity of hardware and
software configurations, as well as third-party dependency compatibility
issues, we cannot guarantee 100% project availability. Therefore, for
users who wish to use this project in non-recommended environments, we
suggest carefully reading the documentation and FAQ first. Most issues
already have corresponding solutions in the FAQ. We also encourage
community feedback to help us gradually expand support.
.. raw:: html
<style>
table, th, td {
border: 1px solid black;
border-collapse: collapse;
}
</style>
<table>
<tr>
<td colspan="3" rowspan="2">Operating System</td>
</tr>
<tr>
<td>Linux after 2019</td>
<td>Windows 10 / 11</td>
<td>macOS 11+</td>
</tr>
<tr>
<td colspan="3">CPU</td>
<td>x86_64 / arm64</td>
<td>x86_64(unsupported ARM Windows)</td>
<td>x86_64 / arm64</td>
</tr>
<tr>
<td colspan="3">Memory Requirements</td>
<td colspan="3">16GB or more, recommended 32GB+</td>
</tr>
<tr>
<td colspan="3">Storage Requirements</td>
<td colspan="3">20GB or more, with a preference for SSD</td>
</tr>
<tr>
<td colspan="3">Python Version</td>
<td colspan="3">3.10~3.13</td>
</tr>
<tr>
<td colspan="3">Nvidia Driver Version</td>
<td>latest (Proprietary Driver)</td>
<td>latest</td>
<td>None</td>
</tr>
<tr>
<td colspan="3">CUDA Environment</td>
<td colspan="2"><a href="https://pytorch.org/get-started/locally/">Refer to the PyTorch official website</a></td>
<td>None</td>
</tr>
<tr>
<td colspan="3">CANN Environment(NPU support)</td>
<td>8.0+(Ascend 910b)</td>
<td>None</td>
<td>None</td>
</tr>
<tr>
<td rowspan="2">GPU/MPS Hardware Support List</td>
<td colspan="2">GPU VRAM 6GB or more</td>
<td colspan="2">All GPUs with Tensor Cores produced from Volta(2017) onwards.<br>
More than 6GB VRAM </td>
<td rowspan="2">Apple silicon</td>
</tr>
</table>
Create an environment
---------------------------
.. code-block:: shell
conda create -n mineru 'python=3.12' -y
conda activate mineru
pip install -U "magic-pdf[full]"
Download model weight files
------------------------------
.. code-block:: shell
pip install huggingface_hub
wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
python download_models_hf.py
Install LibreOffice[Optional]
----------------------------------
This section is required for handle **doc**, **docx**, **ppt**, **pptx** filetype, You can **skip** this section if no need for those filetype processing.
Linux/Macos Platform
""""""""""""""""""""""
.. code::
apt-get/yum/brew install libreoffice
Windows Platform
""""""""""""""""""""
.. code::
install libreoffice
append "install_dir\LibreOffice\program" to ENVIRONMENT PATH
.. tip::
The MinerU is installed, Check out :doc:`../usage/command_line` to convert your first pdf **or** reading the following sections for more details about install
next_docs/en/user_guide/pipe_result.rst deleted 100644 → 0
View file @ 9487d33d
Pipe Result
==============
.. admonition:: Tip
:class: tip
Please first navigate to :doc:`tutorial/pipeline` to get an initial understanding of how the pipeline works; this will help in understanding the content of this section.
The **PipeResult** class is a container for storing pipeline processing results and implements a series of methods related to these results, such as draw_layout, draw_span.
Checkout :doc:`../api/pipe_operators` for more details about **PipeResult**
Structure Definitions
-------------------------------
**some_pdf_middle.json**
+----------------+--------------------------------------------------------------+
| Field Name | Description |
| | |
+================+==============================================================+
| pdf_info | list, each element is a dict representing the parsing result |
| | of each PDF page, see the table below for details |
+----------------+--------------------------------------------------------------+
| \_ | ocr \| txt, used to indicate the mode used in this |
| parse_type | intermediate parsing state |
| | |
+----------------+--------------------------------------------------------------+
| \_version_name | string, indicates the version of magic-pdf used in this |
| | parsing |
| | |
+----------------+--------------------------------------------------------------+
**pdf_info**
Field structure description
+-------------------------+------------------------------------------------------------+
| Field | Description |
| Name | |
+=========================+============================================================+
| preproc_blocks | Intermediate result after PDF preprocessing, not yet |
| | segmented |
+-------------------------+------------------------------------------------------------+
| layout_bboxes | Layout segmentation results, containing layout direction |
| | (vertical, horizontal), and bbox, sorted by reading order |
+-------------------------+------------------------------------------------------------+
| page_idx | Page number, starting from 0 |
| | |
+-------------------------+------------------------------------------------------------+
| page_size | Page width and height |
| | |
+-------------------------+------------------------------------------------------------+
| \_layout_tree | Layout tree structure |
| | |
+-------------------------+------------------------------------------------------------+
| images | list, each element is a dict representing an img_block |
+-------------------------+------------------------------------------------------------+
| tables | list, each element is a dict representing a table_block |
+-------------------------+------------------------------------------------------------+
| interline_equation | list, each element is a dict representing an |
| | interline_equation_block |
| | |
+-------------------------+------------------------------------------------------------+
| discarded_blocks | List, block information returned by the model that needs |
| | to be dropped |
| | |
+-------------------------+------------------------------------------------------------+
| para_blocks | Result after segmenting preproc_blocks |
| | |
+-------------------------+------------------------------------------------------------+
In the above table, ``para_blocks`` is an array of dicts, each dict
representing a block structure. A block can support up to one level of
nesting.
**block**
The outer block is referred to as a first-level block, and the fields in
the first-level block include:
+------------------------+-------------------------------------------------------------+
| Field | Description |
| Name | |
+========================+=============================================================+
| type | Block type (table|image) |
+------------------------+-------------------------------------------------------------+
| bbox | Block bounding box coordinates |
+------------------------+-------------------------------------------------------------+
| blocks | list, each element is a dict representing a second-level |
| | block |
+------------------------+-------------------------------------------------------------+
There are only two types of first-level blocks: “table” and “image”. All
other blocks are second-level blocks.
The fields in a second-level block include:
+----------------------+----------------------------------------------------------------+
| Field | Description |
| Name | |
+======================+================================================================+
| | Block type |
| type | |
+----------------------+----------------------------------------------------------------+
| | Block bounding box coordinates |
| bbox | |
+----------------------+----------------------------------------------------------------+
| | list, each element is a dict representing a line, used to |
| lines | describe the composition of a line of information |
+----------------------+----------------------------------------------------------------+
Detailed explanation of second-level block types
================== ======================
type Description
================== ======================
image_body Main body of the image
image_caption Image description text
table_body Main body of the table
table_caption Table description text
table_footnote Table footnote
text Text block
title Title block
interline_equation Block formula
================== ======================
**line**
The field format of a line is as follows:
+---------------------+----------------------------------------------------------------+
| Field | Description |
| Name | |
+=====================+================================================================+
| | Bounding box coordinates of the line |
| bbox | |
+---------------------+----------------------------------------------------------------+
| spans | list, each element is a dict representing a span, used to |
| | describe the composition of the smallest unit |
+---------------------+----------------------------------------------------------------+
**span**
+---------------------+-----------------------------------------------------------+
| Field | Description |
| Name | |
+=====================+===========================================================+
| bbox | Bounding box coordinates of the span |
+---------------------+-----------------------------------------------------------+
| type | Type of the span |
+---------------------+-----------------------------------------------------------+
| content | Text spans use content, chart spans use img_path to store |
| \| | the actual text or screenshot path information |
| img_path | |
+---------------------+-----------------------------------------------------------+
The types of spans are as follows:
================== ==============
type Description
================== ==============
image Image
table Table
text Text
inline_equation Inline formula
interline_equation Block formula
================== ==============
**Summary**
A span is the smallest storage unit for all elements.
The elements stored within para_blocks are block information.
The block structure is as follows:
First-level block (if any) -> Second-level block -> Line -> Span
.. _example-1:
example
^^^^^^^
.. code:: json
{
"pdf_info": [
{
"preproc_blocks": [
{
"type": "text",
"bbox": [
52,
61.956024169921875,
294,
82.99800872802734
],
"lines": [
{
"bbox": [
52,
61.956024169921875,
294,
72.0000228881836
],
"spans": [
{
"bbox": [
54.0,
61.956024169921875,
296.2261657714844,
72.0000228881836
],
"content": "dependent on the service headway and the reliability of the departure ",
"type": "text",
"score": 1.0
}
]
}
]
}
],
"layout_bboxes": [
{
"layout_bbox": [
52,
61,
294,
731
],
"layout_label": "V",
"sub_layout": []
}
],
"page_idx": 0,
"page_size": [
612.0,
792.0
],
"_layout_tree": [],
"images": [],
"tables": [],
"interline_equations": [],
"discarded_blocks": [],
"para_blocks": [
{
"type": "text",
"bbox": [
52,
61.956024169921875,
294,
82.99800872802734
],
"lines": [
{
"bbox": [
52,
61.956024169921875,
294,
72.0000228881836
],
"spans": [
{
"bbox": [
54.0,
61.956024169921875,
296.2261657714844,
72.0000228881836
],
"content": "dependent on the service headway and the reliability of the departure ",
"type": "text",
"score": 1.0
}
]
}
]
}
]
}
],
"_parse_type": "txt",
"_version_name": "0.6.1"
}
Pipeline Result
------------------
.. code:: python
from magic_pdf.pdf_parse_union_core_v2 import pdf_parse_union
from magic_pdf.operators.pipes import PipeResult
from magic_pdf.data.dataset import Dataset
res = pdf_parse_union(*args, **kwargs)
res['_parse_type'] = PARSE_TYPE_OCR
res['_version_name'] = __version__
if 'lang' in kwargs and kwargs['lang'] is not None:
res['lang'] = kwargs['lang']
dataset : Dataset = some_dataset # not real dataset
pipeResult = PipeResult(res, dataset)
some_pdf_layout.pdf
~~~~~~~~~~~~~~~~~~~
Each page layout consists of one or more boxes. The number at the top
left of each box indicates its sequence number. Additionally, in
``layout.pdf``, different content blocks are highlighted with different
background colors.
.. figure:: ../_static/image/layout_example.png
:alt: layout example
layout example
some_pdf_spans.pdf
~~~~~~~~~~~~~~~~~~
All spans on the page are drawn with different colored line frames
according to the span type. This file can be used for quality control,
allowing for quick identification of issues such as missing text or
unrecognized inline formulas.
.. figure:: ../_static/image/spans_example.png
:alt: spans example
spans example
next_docs/en/user_guide/quick_start.rst deleted 100644 → 0
View file @ 9487d33d
Quick Start
==============
Want to learn about the usage methods under different scenarios ? This page gives good examples about multiple usage cases match your needs.
.. toctree::
:maxdepth: 1
quick_start/convert_pdf
quick_start/convert_image
quick_start/convert_ms_office
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment