Skip to content

GitLab

Unverified Commit 845a3ff0 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Merge pull request #969 from opendatalab/release-0.9.3 

Release 0.9.3
parents d0558abb 6083e109
Hide whitespace changes
Inline Side-by-side
Showing with 820 additions and 134 deletions
magic_pdf/model/ppTableModel.py → magic_pdf/model/sub_modules/table/tablemaster/tablemaster_paddle.py
View file @ 845a3ff0
......@@ -7,7 +7,7 @@ from PIL import Image
import numpy as np
class ppTableModel(object):
class TableMasterPaddleModel(object):
"""
This class is responsible for converting image of table into HTML format using a pre-trained model.
......
magic_pdf/para/para_split_v3.py
View file @ 845a3ff0
......@@ -77,14 +77,12 @@ def __is_list_or_index_block(block):
# 如果首行左边不顶格而右边顶格,末行左边顶格而右边不顶格 （第一行可能可以右边不顶格）
if (first_line['bbox'][0] - block['bbox_fs'][0] > line_height / 2 and
# block['bbox_fs'][2] - first_line['bbox'][2] < line_height and
abs(last_line['bbox'][0] - block['bbox_fs'][0]) < line_height / 2 and
block['bbox_fs'][2] - last_line['bbox'][2] > line_height
):
multiple_para_flag = True
for line in block['lines']:
line_mid_x = (line['bbox'][0] + line['bbox'][2]) / 2
block_mid_x = (block['bbox_fs'][0] + block['bbox_fs'][2]) / 2
if (
......@@ -102,13 +100,13 @@ def __is_list_or_index_block(block):
if span_type == ContentType.Text:
line_text += span['content'].strip()
# 添加所有文本，包括空行，保持与block['lines']长度一致
lines_text_list.append(line_text)
# 计算line左侧顶格数量是否大于2，是否顶格用abs(block['bbox_fs'][0] - line['bbox'][0]) < line_height/2 来判断
if abs(block['bbox_fs'][0] - line['bbox'][0]) < line_height / 2:
left_close_num += 1
elif line['bbox'][0] - block['bbox_fs'][0] > line_height:
# logger.info(f"{line_text}, {block['bbox_fs']}, {line['bbox']}")
left_not_close_num += 1
# 计算右侧是否顶格
......@@ -117,7 +115,6 @@ def __is_list_or_index_block(block):
else:
# 右侧不顶格情况下是否有一段距离，拍脑袋用0.3block宽度做阈值
closed_area = 0.26 * block_weight
# closed_area = 5 * line_height
if block['bbox_fs'][2] - line['bbox'][2] > closed_area:
right_not_close_num += 1
......@@ -128,6 +125,7 @@ def __is_list_or_index_block(block):
num_start_count = 0
num_end_count = 0
flag_end_count = 0
if len(lines_text_list) > 0:
for line_text in lines_text_list:
if len(line_text) > 0:
......@@ -138,11 +136,10 @@ def __is_list_or_index_block(block):
if line_text[-1].isdigit():
num_end_count += 1
if flag_end_count / len(lines_text_list) >= 0.8:
line_end_flag = True
if num_start_count / len(lines_text_list) >= 0.8 or num_end_count / len(lines_text_list) >= 0.8:
line_num_flag = True
if flag_end_count / len(lines_text_list) >= 0.8:
line_end_flag = True
# 有的目录右侧不贴边, 目前认为左边或者右边有一边全贴边，且符合数字规则极为index
if ((left_close_num / len(block['lines']) >= 0.8 or right_close_num / len(block['lines']) >= 0.8)
......@@ -176,7 +173,7 @@ def __is_list_or_index_block(block):
# 这种是大部分line item 都有结束标识符的情况，按结束标识符区分不同item
elif line_end_flag:
for i, line in enumerate(block['lines']):
if lines_text_list[i][-1] in LIST_END_FLAG:
if len(lines_text_list[i]) > 0 and lines_text_list[i][-1] in LIST_END_FLAG:
line[ListLineTag.IS_LIST_END_LINE] = True
if i + 1 < len(block['lines']):
block['lines'][i + 1][ListLineTag.IS_LIST_START_LINE] = True
......@@ -187,17 +184,18 @@ def __is_list_or_index_block(block):
if line_start_flag:
line[ListLineTag.IS_LIST_START_LINE] = True
line_start_flag = False
# elif abs(block['bbox_fs'][2] - line['bbox'][2]) > line_height:
if abs(block['bbox_fs'][2] - line['bbox'][2]) > 0.1 * block_weight:
line[ListLineTag.IS_LIST_END_LINE] = True
line_start_flag = True
# 一种有缩进的特殊有序list,start line 左侧不贴边且以数字开头，end line 以 IS_LIST_END_LINE 结尾且数量和start line 一致
elif num_start_count >= 2 and num_start_count == flag_end_count: # 简单一点先不考虑左侧不贴边的情况
# 一种有缩进的特殊有序list,start line 左侧不贴边且以数字开头，end line 以 IS_LIST_END_FLAG 结尾且数量和start line 一致
elif num_start_count >= 2 and num_start_count == flag_end_count:
for i, line in enumerate(block['lines']):
if lines_text_list[i][0].isdigit():
line[ListLineTag.IS_LIST_START_LINE] = True
if lines_text_list[i][-1] in LIST_END_FLAG:
line[ListLineTag.IS_LIST_END_LINE] = True
if len(lines_text_list[i]) > 0:
if lines_text_list[i][0].isdigit():
line[ListLineTag.IS_LIST_START_LINE] = True
if lines_text_list[i][-1] in LIST_END_FLAG:
line[ListLineTag.IS_LIST_END_LINE] = True
else:
# 正常有缩进的list处理
for line in block['lines']:
......
magic_pdf/pdf_parse_union_core_v2.py
View file @ 845a3ff0
......@@ -30,8 +30,8 @@ from magic_pdf.pre_proc.equations_replace import (
from magic_pdf.pre_proc.ocr_detect_all_bboxes import \
ocr_prepare_bboxes_for_layout_split_v2
from magic_pdf.pre_proc.ocr_dict_merge import (fill_spans_in_blocks,
fix_block_spans,
fix_discarded_block, fix_block_spans_v2)
fix_discarded_block,
fix_block_spans_v2)
from magic_pdf.pre_proc.ocr_span_list_modify import (
get_qa_need_list_v2, remove_overlaps_low_confidence_spans,
remove_overlaps_min_spans)
......@@ -164,8 +164,8 @@ class ModelSingleton:
def do_predict(boxes: List[List[int]], model) -> List[int]:
from magic_pdf.model.v3.helpers import (boxes2inputs, parse_logits,
prepare_inputs)
from magic_pdf.model.sub_modules.reading_oreder.layoutreader.helpers import (boxes2inputs, parse_logits,
prepare_inputs)
inputs = boxes2inputs(boxes)
inputs = prepare_inputs(inputs, model)
......@@ -174,23 +174,57 @@ def do_predict(boxes: List[List[int]], model) -> List[int]:
def cal_block_index(fix_blocks, sorted_bboxes):
for block in fix_blocks:
line_index_list = []
if len(block['lines']) == 0:
block['index'] = sorted_bboxes.index(block['bbox'])
else:
if sorted_bboxes is not None:
# 使用layoutreader排序
for block in fix_blocks:
line_index_list = []
if len(block['lines']) == 0:
block['index'] = sorted_bboxes.index(block['bbox'])
else:
for line in block['lines']:
line['index'] = sorted_bboxes.index(line['bbox'])
line_index_list.append(line['index'])
median_value = statistics.median(line_index_list)
block['index'] = median_value
# 删除图表body block中的虚拟line信息, 并用real_lines信息回填
if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
block['virtual_lines'] = copy.deepcopy(block['lines'])
block['lines'] = copy.deepcopy(block['real_lines'])
del block['real_lines']
else:
# 使用xycut排序
block_bboxes = []
for block in fix_blocks:
block_bboxes.append(block['bbox'])
# 删除图表body block中的虚拟line信息, 并用real_lines信息回填
if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
block['virtual_lines'] = copy.deepcopy(block['lines'])
block['lines'] = copy.deepcopy(block['real_lines'])
del block['real_lines']
import numpy as np
from magic_pdf.model.sub_modules.reading_oreder.layoutreader.xycut import recursive_xy_cut
random_boxes = np.array(block_bboxes)
np.random.shuffle(random_boxes)
res = []
recursive_xy_cut(np.asarray(random_boxes).astype(int), np.arange(len(block_bboxes)), res)
assert len(res) == len(block_bboxes)
sorted_boxes = random_boxes[np.array(res)].tolist()
for i, block in enumerate(fix_blocks):
block['index'] = sorted_boxes.index(block['bbox'])
# 生成line index
sorted_blocks = sorted(fix_blocks, key=lambda b: b['index'])
line_inedx = 1
for block in sorted_blocks:
for line in block['lines']:
line['index'] = sorted_bboxes.index(line['bbox'])
line_index_list.append(line['index'])
median_value = statistics.median(line_index_list)
block['index'] = median_value
# 删除图表body block中的虚拟line信息, 并用real_lines信息回填
if block['type'] in [BlockType.ImageBody, BlockType.TableBody]:
block['virtual_lines'] = copy.deepcopy(block['lines'])
block['lines'] = copy.deepcopy(block['real_lines'])
del block['real_lines']
line['index'] = line_inedx
line_inedx += 1
return fix_blocks
......@@ -264,6 +298,9 @@ def sort_lines_by_model(fix_blocks, page_w, page_h, line_height):
block['lines'].append({'bbox': line, 'spans': []})
page_line_list.extend(lines)
if len(page_line_list) > 200: # layoutreader最高支持512line
return None
# 使用layoutreader排序
x_scale = 1000.0 / page_w
y_scale = 1000.0 / page_h
......
magic_pdf/resources/model_config/model_configs.yaml
View file @ 845a3ff0
......@@ -4,4 +4,5 @@ weights:
yolo_v8_mfd: MFD/YOLO/yolo_v8_ft.pt
unimernet_small: MFR/unimernet_small
struct_eqtable: TabRec/StructEqTable
tablemaster: TabRec/TableMaster
\ No newline at end of file
tablemaster: TabRec/TableMaster
rapid_table: TabRec/RapidTable
\ No newline at end of file
magic_pdf/tools/common.py
View file @ 845a3ff0
......@@ -14,6 +14,9 @@ from magic_pdf.pipe.TXTPipe import TXTPipe
from magic_pdf.pipe.UNIPipe import UNIPipe
from magic_pdf.rw.AbsReaderWriter import AbsReaderWriter
from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
import fitz
# from io import BytesIO
# from pypdf import PdfReader, PdfWriter
def prepare_env(output_dir, pdf_file_name, method):
......@@ -26,6 +29,42 @@ def prepare_env(output_dir, pdf_file_name, method):
return local_image_dir, local_md_dir
# def convert_pdf_bytes_to_bytes_by_pypdf(pdf_bytes, start_page_id=0, end_page_id=None):
# # 将字节数据包装在 BytesIO 对象中
# pdf_file = BytesIO(pdf_bytes)
# # 读取 PDF 的字节数据
# reader = PdfReader(pdf_file)
# # 创建一个新的 PDF 写入器
# writer = PdfWriter()
# # 将所有页面添加到新的 PDF 写入器中
# end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(reader.pages) - 1
# if end_page_id > len(reader.pages) - 1:
# logger.warning("end_page_id is out of range, use pdf_docs length")
# end_page_id = len(reader.pages) - 1
# for i, page in enumerate(reader.pages):
# if start_page_id <= i <= end_page_id:
# writer.add_page(page)
# # 创建一个字节缓冲区来存储输出的 PDF 数据
# output_buffer = BytesIO()
# # 将 PDF 写入字节缓冲区
# writer.write(output_buffer)
# # 获取字节缓冲区的内容
# converted_pdf_bytes = output_buffer.getvalue()
# return converted_pdf_bytes
def convert_pdf_bytes_to_bytes_by_pymupdf(pdf_bytes, start_page_id=0, end_page_id=None):
document = fitz.open("pdf", pdf_bytes)
output_document = fitz.open()
end_page_id = end_page_id if end_page_id is not None and end_page_id >= 0 else len(document) - 1
if end_page_id > len(document) - 1:
logger.warning("end_page_id is out of range, use pdf_docs length")
end_page_id = len(document) - 1
output_document.insert_pdf(document, from_page=start_page_id, to_page=end_page_id)
output_bytes = output_document.tobytes()
return output_bytes
def do_parse(
output_dir,
pdf_file_name,
......@@ -55,6 +94,8 @@ def do_parse(
f_draw_model_bbox = True
f_draw_line_sort_bbox = True
pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf(pdf_bytes, start_page_id, end_page_id)
orig_model_list = copy.deepcopy(model_list)
local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name,
parse_method)
......@@ -66,15 +107,18 @@ def do_parse(
if parse_method == 'auto':
jso_useful_key = {'_pdf_type': '', 'model_list': model_list}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
# start_page_id=start_page_id, end_page_id=end_page_id,
lang=lang,
layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
elif parse_method == 'txt':
pipe = TXTPipe(pdf_bytes, model_list, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
# start_page_id=start_page_id, end_page_id=end_page_id,
lang=lang,
layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
elif parse_method == 'ocr':
pipe = OCRPipe(pdf_bytes, model_list, image_writer, is_debug=True,
start_page_id=start_page_id, end_page_id=end_page_id, lang=lang,
# start_page_id=start_page_id, end_page_id=end_page_id,
lang=lang,
layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
else:
logger.error('unknown parse method')
......
next_docs/README.md 0 → 100644
View file @ 845a3ff0
<div align="center" xmlns="http://www.w3.org/1999/html">
<!-- logo -->
<p align="center">
<img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
</p>
<!-- icon -->
[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjIzIiBoZWlnaHQ9IjIwMCIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KCiA8Zz4KICA8dGl0bGU+TGF5ZXIgMTwvdGl0bGU+CiAgPHBhdGggaWQ9InN2Z18xNCIgZmlsbD0iIzYyNGFmZiIgZD0ibTAsODkuODRsMjUuNjUsMGwwLDI1LjY0OTk5bC0yNS42NSwwbDAsLTI1LjY0OTk5eiIvPgogIDxwYXRoIGlkPSJzdmdfMTUiIGZpbGw9IiM2MjRhZmYiIGQ9Im05OS4xNCwxMTUuNDlsMjUuNjUsMGwwLDI1LjY1bC0yNS42NSwwbDAsLTI1LjY1eiIvPgogIDxwYXRoIGlkPSJzdmdfMTYiIGZpbGw9IiM2MjRhZmYiIGQ9Im0xNzYuMDksMTQxLjE0bC0yNS42NDk5OSwwbDAsMjIuMTlsNDcuODQsMGwwLC00Ny44NGwtMjIuMTksMGwwLDI1LjY1eiIvPgogIDxwYXRoIGlkPSJzdmdfMTciIGZpbGw9IiMzNmNmZDEiIGQ9Im0xMjQuNzksODkuODRsMjUuNjUsMGwwLDI1LjY0OTk5bC0yNS42NSwwbDAsLTI1LjY0OTk5eiIvPgogIDxwYXRoIGlkPSJzdmdfMTgiIGZpbGw9IiMzNmNmZDEiIGQ9Im0wLDY0LjE5bDI1LjY1LDBsMCwyNS42NWwtMjUuNjUsMGwwLC0yNS42NXoiLz4KICA8cGF0aCBpZD0ic3ZnXzE5IiBmaWxsPSIjNjI0YWZmIiBkPSJtMTk4LjI4LDg5Ljg0bDI1LjY0OTk5LDBsMCwyNS42NDk5OWwtMjUuNjQ5OTksMGwwLC0yNS42NDk5OXoiLz4KICA8cGF0aCBpZD0ic3ZnXzIwIiBmaWxsPSIjMzZjZmQxIiBkPSJtMTk4LjI4LDY0LjE5bDI1LjY0OTk5LDBsMCwyNS42NWwtMjUuNjQ5OTksMGwwLC0yNS42NXoiLz4KICA8cGF0aCBpZD0ic3ZnXzIxIiBmaWxsPSIjNjI0YWZmIiBkPSJtMTUwLjQ0LDQybDAsMjIuMTlsMjUuNjQ5OTksMGwwLDI1LjY1bDIyLjE5LDBsMCwtNDcuODRsLTQ3Ljg0LDB6Ii8+CiAgPHBhdGggaWQ9InN2Z18yMiIgZmlsbD0iIzM2Y2ZkMSIgZD0ibTczLjQ5LDg5Ljg0bDI1LjY1LDBsMCwyNS42NDk5OWwtMjUuNjUsMGwwLC0yNS42NDk5OXoiLz4KICA8cGF0aCBpZD0ic3ZnXzIzIiBmaWxsPSIjNjI0YWZmIiBkPSJtNDcuODQsNjQuMTlsMjUuNjUsMGwwLC0yMi4xOWwtNDcuODQsMGwwLDQ3Ljg0bDIyLjE5LDBsMCwtMjUuNjV6Ii8+CiAgPHBhdGggaWQ9InN2Z18yNCIgZmlsbD0iIzYyNGFmZiIgZD0ibTQ3Ljg0LDExNS40OWwtMjIuMTksMGwwLDQ3Ljg0bDQ3Ljg0LDBsMCwtMjIuMTlsLTI1LjY1LDBsMCwtMjUuNjV6Ii8+CiA8L2c+Cjwvc3ZnPg==&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
<!-- language -->
[English](README.md) | [简体中文](README_zh-CN.md)
<!-- hot link -->
<p align="center">
<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: High-Quality PDF Extraction Toolkit</a>🔥🔥🔥
</p>
<!-- join us -->
<p align="center">
👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<p align="center">
read more docs on <a href="https://mineru.readthedocs.io/en/latest/"> Read The Docs </a>
</p>
</div>
# Changelog
- 2024/11/06 0.9.2 released. Integrated the [StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B) model for table recognition functionality.
- 2024/10/31 0.9.0 released. This is a major new version with extensive code refactoring, addressing numerous issues, improving performance, reducing hardware requirements, and enhancing usability:
- Refactored the sorting module code to use [layoutreader](https://github.com/ppaanngggg/layoutreader) for reading order sorting, ensuring high accuracy in various layouts.
- Refactored the paragraph concatenation module to achieve good results in cross-column, cross-page, cross-figure, and cross-table scenarios.
- Refactored the list and table of contents recognition functions, significantly improving the accuracy of list blocks and table of contents blocks, as well as the parsing of corresponding text paragraphs.
- Refactored the matching logic for figures, tables, and descriptive text, greatly enhancing the accuracy of matching captions and footnotes to figures and tables, and reducing the loss rate of descriptive text to near zero.
- Added multi-language support for OCR, supporting detection and recognition of 84 languages.For the list of supported languages, see [OCR Language Support List](https://paddlepaddle.github.io/PaddleOCR/latest/en/ppocr/blog/multi_languages.html#5-support-languages-and-abbreviations).
- Added memory recycling logic and other memory optimization measures, significantly reducing memory usage. The memory requirement for enabling all acceleration features except table acceleration (layout/formula/OCR) has been reduced from 16GB to 8GB, and the memory requirement for enabling all acceleration features has been reduced from 24GB to 10GB.
- Optimized configuration file feature switches, adding an independent formula detection switch to significantly improve speed and parsing results when formula detection is not needed.
- Integrated [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit):
- Added the self-developed `doclayout_yolo` model, which speeds up processing by more than 10 times compared to the original solution while maintaining similar parsing effects, and can be freely switched with `layoutlmv3` via the configuration file.
- Upgraded formula parsing to `unimernet 0.2.1`, improving formula parsing accuracy while significantly reducing memory usage.
- Due to the repository change for `PDF-Extract-Kit 1.0`, you need to re-download the model. Please refer to [How to Download Models](docs/how_to_download_models_en.md) for detailed steps.
- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a [localized deployment version](projects/web_demo/README.md) of the [online demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/) and the [front-end interface](projects/web/README.md).
- 2024/09/09: Version 0.8.0 released, supporting fast deployment with Dockerfile, and launching demos on Huggingface and Modelscope.
- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table recognition option
- 2024/08/09: Version 0.7.0b1 released, simplified installation process, added table recognition functionality
- 2024/08/01: Version 0.6.2b1 released, optimized dependency conflict issues and installation documentation
- 2024/07/05: Initial open-source release
<!-- TABLE OF CONTENT -->
<details open="open">
<summary><h2 style="display: inline-block">Table of Contents</h2></summary>
<ol>
<li>
<a href="#mineru">MinerU</a>
<ul>
<li><a href="#project-introduction">Project Introduction</a></li>
<li><a href="#key-features">Key Features</a></li>
<li><a href="#quick-start">Quick Start</a>
<ul>
<li><a href="#online-demo">Online Demo</a></li>
<li><a href="#quick-cpu-demo">Quick CPU Demo</a></li>
</ul>
</li>
<li><a href="#usage">Usage</a>
<ul>
<li><a href="#api">API</a></li>
<li><a href="#deploy-derived-projects">Deploy Derived Projects</a></li>
<li><a href="#development-guide">Development Guide</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#todo">TODO</a></li>
<li><a href="#all-thanks-to-our-contributors">All Thanks To Our Contributors</a></li>
<li><a href="#license-information">License Information</a></li>
<li><a href="#acknowledgments">Acknowledgments</a></li>
<li><a href="#citation">Citation</a></li>
<li><a href="#star-history">Star History</a></li>
<li><a href="#magic-doc">Magic-doc</a></li>
<li><a href="#magic-html">Magic-html</a></li>
<li><a href="#links">Links</a></li>
</ol>
</details>
# MinerU
## 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**.
https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
## Quick Start
There are multiple different ways to experience MinerU:
- [Online Demo (No Installation Required)](#online-demo)
- [Quick CPU Demo (Windows, Linux, Mac)](#quick-cpu-demo)
### Online Demo
Stable Version (Stable version verified by QA):
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
Test Version (Synced with dev branch updates, testing new features):
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAF8AAABYCAMAAACkl9t/AAAAk1BMVEVHcEz/nQv/nQv/nQr/nQv/nQr/nQv/nQv/nQr/wRf/txT/pg7/yRr/rBD/zRz/ngv/oAz/zhz/nwv/txT/ngv/0B3+zBz/nQv/0h7/wxn/vRb/thXkuiT/rxH/pxD/ogzcqyf/nQvTlSz/czCxky7/SjifdjT/Mj3+Mj3wMj15aTnDNz+DSD9RTUBsP0FRO0Q6O0WyIxEIAAAAGHRSTlMADB8zSWF3krDDw8TJ1NbX5efv8ff9/fxKDJ9uAAAGKklEQVR42u2Z63qjOAyGC4RwCOfB2JAGqrSb2WnTw/1f3UaWcSGYNKTdf/P+mOkTrE+yJBulvfvLT2A5ruenaVHyIks33npl/6C4s/ZLAM45SOi/1FtZPyFur1OYofBX3w7d54Bxm+E8db+nDr12ttmESZ4zludJEG5S7TO72YPlKZFyE+YCYUJTBZsMiNS5Sd7NlDmKM2Eg2JQg8awbglfqgbhArjxkS7dgp2RH6hc9AMLdZYUtZN5DJr4molC8BfKrEkPKEnEVjLbgW1fLy77ZVOJagoIcLIl+IxaQZGjiX597HopF5CkaXVMDO9Pyix3AFV3kw4lQLCbHuMovz8FallbcQIJ5Ta0vks9RnolbCK84BtjKRS5uA43hYoZcOBGIG2Epbv6CvFVQ8m8loh66WNySsnN7htL58LNp+NXT8/PhXiBXPMjLSxtwp8W9f/1AngRierBkA+kk/IpUSOeKByzn8y3kAAAfh//0oXgV4roHm/kz4E2z//zRc3/lgwBzbM2mJxQEa5pqgX7d1L0htrhx7LKxOZlKbwcAWyEOWqYSI8YPtgDQVjpB5nvaHaSnBaQSD6hweDi8PosxD6/PT09YY3xQA7LTCTKfYX+QHpA0GCcqmEHvr/cyfKQTEuwgbs2kPxJEB0iNjfJcCTPyocx+A0griHSmADiC91oNGVwJ69RudYe65vJmoqfpul0lrqXadW0jFKH5BKwAeCq+Den7s+3zfRJzA61/Uj/9H/VzLKTx9jFPPdXeeP+L7WEvDLAKAIoF8bPTKT0+TM7W8ePj3Rz/Yn3kOAp2f1Kf0Weony7pn/cPydvhQYV+eFOfmOu7VB/ViPe34/EN3RFHY/yRuT8ddCtMPH/McBAT5s+vRde/gf2c/sPsjLK+m5IBQF5tO+h2tTlBGnP6693JdsvofjOPnnEHkh2TnV/X1fBl9S5zrwuwF8NFrAVJVwCAPTe8gaJlomqlp0pv4Pjn98tJ/t/fL++6unpR1YGC2n/KCoa0tTLoKiEeUPDl94nj+5/Tv3/eT5vBQ60X1S0oZr+IWRR8Ldhu7AlLjPISlJcO9vrFotky9SpzDequlwEir5beYAc0R7D9KS1DXva0jhYRDXoExPdc6yw5GShkZXe9QdO/uOvHofxjrV/TNS6iMJS+4TcSTgk9n5agJdBQbB//IfF/HpvPt3Tbi7b6I6K0R72p6ajryEJrENW2bbeVUGjfgoals4L443c7BEE4mJO2SpbRngxQrAKRudRzGQ8jVOL2qDVjjI8K1gc3TIJ5KiFZ1q+gdsARPB4NQS4AjwVSt72DSoXNyOWUrU5mQ9nRYyjp89Xo7oRI6Bga9QNT1mQ/ptaJq5T/7WcgAZywR/XlPGAUDdet3LE+qS0TI+g+aJU8MIqjo0Kx8Ly+maxLjJmjQ18rA0YCkxLQbUZP1WqdmyQGJLUm7VnQFqodmXSqmRrdVpqdzk5LvmvgtEcW8PMGdaS23EOWyDVbACZzUJPaqMbjDxpA3Qrgl0AikimGDbqmyT8P8NOYiqrldF8rX+YN7TopX4UoHuSCYY7cgX4gHwclQKl1zhx0THf+tCAUValzjI7Wg9EhptrkIcfIJjA94evOn8B2eHaVzvBrnl2ig0So6hvPaz0IGcOvTHvUIlE2+prqAxLSQxZlU2stql1NqCCLdIiIN/i1DBEHUoElM9dBravbiAnKqgpi4IBkw+utSPIoBijDXJipSVV7MpOEJUAc5Qmm3BnUN+w3hteEieYKfRZSIUcXKMVf0u5wD4EwsUNVvZOtUT7A2GkffHjByWpHqvRBYrTV72a6j8zZ6W0DTE86Hn04bmyWX3Ri9WH7ZU6Q7h+ZHo0nHUAcsQvVhXRDZHChwiyi/hnPuOsSEF6Exk3o6Y9DT1eZ+6cASXk2Y9k+6EOQMDGm6WBK10wOQJCBwren86cPPWUcRAnTVjGcU1LBgs9FURiX/e6479yZcLwCBmTxiawEwrOcleuu12t3tbLv/N4RLYIBhYexm7Fcn4OJcn0+zc+s8/VfPeddZHAGN6TT8eGczHdR/Gts1/MzDkThr23zqrVfAMFT33Nx1RJsx1k5zuWILLnG/vsH+Fv5D4NTVcp1Gzo8AAAAAElFTkSuQmCC&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
### Quick CPU Demo
#### 1. Install magic-pdf
```bash
conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
```
#### 2. Download model weight files
Refer to [How to Download Model Files](docs/how_to_download_models_en.md) for detailed instructions.
#### 3. Modify the Configuration File for Additional Configuration
After completing the [2. Download model weight files](#2-download-model-weight-files) 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】.
> [!TIP]
> The user directory for Windows is "C:\\Users\\username", for Linux it is "/home/username", and for macOS it is "/Users/username".
You can modify certain configurations in this file to enable or disable features, such as table recognition:
> [!NOTE]
> If the following items are not present in the JSON, please manually add the required items and remove the comment content (standard JSON does not support comments).
```json
{
// other config
"layout-config": {
"model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true // The formula recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
},
"table-config": {
"model": "rapid_table", // Default to using "rapid_table", can be switched to "tablemaster" or "struct_eqtable".
"enable": false, // The table recognition feature is disabled by default. If you need to enable it, please change the value here to "true".
"max_time": 400
}
}
```
## Usage
### API
Processing files from local disk
```python
image_writer = DiskReaderWriter(local_image_dir)
image_dir = str(os.path.basename(local_image_dir))
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
Processing files from object storage
```python
s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
image_dir = "s3://img_bucket/"
s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
For detailed implementation, refer to:
- [demo.py Simplest Processing Method](demo/demo.py)
- [magic_pdf_parse_main.py More Detailed Processing Workflow](demo/magic_pdf_parse_main.py)
### Deploy Derived Projects
Derived projects include secondary development projects based on MinerU by project developers and community developers,
such as application interfaces based on Gradio, RAG based on llama, web demos similar to the official website, lightweight multi-GPU load balancing client/server ends, etc.
These projects may offer more features and a better user experience.
For specific deployment methods, please refer to the [Derived Project README](projects/README.md)
### Development Guide
TODO
# TODO
- [x] Reading order based on the model
- [x] Recognition of `index` and `list` in the main text
- [x] Table recognition
- [ ] Code block recognition in the main text
- [ ] [Chemical formula recognition](docs/chemical_knowledge_introduction/introduction.pdf)
- [ ] Geometric shape recognition
# All Thanks To Our Contributors
<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
<img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
</a>
# License Information
[LICENSE.md](LICENSE.md)
This project currently uses PyMuPDF to achieve advanced functionality. However, since it adheres to the AGPL license, it may impose restrictions on certain usage scenarios. In future iterations, we plan to explore and replace it with a more permissive PDF processing library to enhance user-friendliness and flexibility.
# Acknowledgments
- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
- [RapidTable](https://github.com/RapidAI/RapidTable)
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
- [layoutreader](https://github.com/ppaanngggg/layoutreader)
- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
# Citation
```bibtex
@misc{wang2024mineruopensourcesolutionprecise,
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
journal={arXiv preprint arXiv:2407.13773},
year={2024}
}
```
# Star History
<a>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
</picture>
</a>
# Magic-doc
[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
# Magic-html
[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
# Links
- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)
next_docs/README_zh-CN.md 0 → 100644
View file @ 845a3ff0
<div align="center" xmlns="http://www.w3.org/1999/html">
<!-- logo -->
<p align="center">
<img src="docs/images/MinerU-logo.png" width="300px" style="vertical-align:middle;">
</p>
<!-- icon -->
[![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
[![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
[![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/myhloli/3b3a00a4a0a61577b6c30f989092d20d/mineru_demo.ipynb)
[![Paper](https://img.shields.io/badge/Paper-arXiv-green)](https://arxiv.org/abs/2409.18839)
<a href="https://trendshift.io/repositories/11174" target="_blank"><img src="https://trendshift.io/api/badge/repositories/11174" alt="opendatalab%2FMinerU | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
<!-- language -->
[English](README.md) | [简体中文](README_zh-CN.md)
<!-- hot link -->
<p align="center">
<a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: 高质量PDF解析工具箱</a>🔥🔥🔥
</p>
<!-- join us -->
<p align="center">
👋 join us on <a href="https://discord.gg/Tdedn9GTXq" target="_blank">Discord</a> and <a href="https://cdn.vansin.top/internlm/mineru.jpg" target="_blank">WeChat</a>
</p>
<!-- read the docs -->
<p align="center">
read more docs on <a href="https://mineru.readthedocs.io/zh-cn/latest/"> Read The Docs </a>
</p>
</div>
# 更新记录
- 2024/11/06 0.9.2发布，为表格识别功能接入了[StructTable-InternVL2-1B](https://huggingface.co/U4R/StructTable-InternVL2-1B)模型
- 2024/10/31 0.9.0发布，这是我们进行了大量代码重构的全新版本，解决了众多问题，提升了性能，降低了硬件需求，并提供了更丰富的易用性：
- 重构排序模块代码，使用 [layoutreader](https://github.com/ppaanngggg/layoutreader) 进行阅读顺序排序，确保在各种排版下都能实现极高准确率
- 重构段落拼接模块，在跨栏、跨页、跨图、跨表情况下均能实现良好的段落拼接效果
- 重构列表和目录识别功能，极大提升列表块和目录块识别的准确率及对应文本段落的解析效果
- 重构图、表与描述性文本的匹配逻辑，大幅提升 caption 和 footnote 与图表的匹配准确率，并将描述性文本的丢失率降至接近0
- 增加 OCR 的多语言支持，支持 84 种语言的检测与识别，语言支持列表详见 [OCR 语言支持列表](https://paddlepaddle.github.io/PaddleOCR/latest/ppocr/blog/multi_languages.html#5)
- 增加显存回收逻辑及其他显存优化措施，大幅降低显存使用需求。开启除表格加速外的全部加速功能(layout/公式/OCR)的显存需求从16GB降至8GB，开启全部加速功能的显存需求从24GB降至10GB
- 优化配置文件的功能开关，增加独立的公式检测开关，无需公式检测时可大幅提升速度和解析效果
- 集成 [PDF-Extract-Kit 1.0](https://github.com/opendatalab/PDF-Extract-Kit)
- 加入自研的 `doclayout_yolo` 模型，在相近解析效果情况下比原方案提速10倍以上，可通过配置文件与 `layoutlmv3` 自由切换
- 公式解析升级至 `unimernet 0.2.1`，在提升公式解析准确率的同时，大幅降低显存需求
- 因 `PDF-Extract-Kit 1.0` 更换仓库，需要重新下载模型，步骤详见 [如何下载模型](docs/how_to_download_models_zh_cn.md)
- 2024/09/27 0.8.1发布，修复了一些bug，同时提供了[在线demo](https://opendatalab.com/OpenSourceTools/Extractor/PDF/)的[本地化部署版本](projects/web_demo/README_zh-CN.md)和[前端界面](projects/web/README_zh-CN.md)
- 2024/09/09 0.8.0发布，支持Dockerfile快速部署，同时上线了huggingface、modelscope demo
- 2024/08/30 0.7.1发布，集成了paddle tablemaster表格识别功能
- 2024/08/09 0.7.0b1发布，简化安装步骤提升易用性，加入表格识别功能
- 2024/08/01 0.6.2b1发布，优化了依赖冲突问题和安装文档
- 2024/07/05 首次开源
<!-- TABLE OF CONTENT -->
<details open="open">
<summary><h2 style="display: inline-block">文档目录</h2></summary>
<ol>
<li>
<a href="#mineru">MinerU</a>
<ul>
<li><a href="#项目简介">项目简介</a></li>
<li><a href="#主要功能">主要功能</a></li>
<li><a href="#快速开始">快速开始</a>
<ul>
<li><a href="#在线体验">在线体验</a></li>
<li><a href="#使用CPU快速体验">使用CPU快速体验</a></li>
</ul>
</li>
<li><a href="#使用">使用方式</a>
<ul>
<li><a href="#api">API</a></li>
<li><a href="#部署衍生项目">部署衍生项目</a></li>
<li><a href="#二次开发">二次开发</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#todo">TODO</a></li>
<li><a href="#known-issues">Known Issues</a></li>
<li><a href="#faq">FAQ</a></li>
<li><a href="#all-thanks-to-our-contributors">Contributors</a></li>
<li><a href="#license-information">License Information</a></li>
<li><a href="#acknowledgments">Acknowledgements</a></li>
<li><a href="#citation">Citation</a></li>
<li><a href="#star-history">Star History</a></li>
<li><a href="#magic-doc">magic-doc快速提取PPT/DOC/PDF</a></li>
<li><a href="#magic-html">magic-html提取混合网页内容</a></li>
<li><a href="#links">Links</a></li>
</ol>
</details>
# MinerU
## 项目简介
MinerU是一款将PDF转化为机器可读格式的工具（如markdown、json），可以很方便地抽取为任意格式。
MinerU诞生于[书生-浦语](https://github.com/InternLM/InternLM)的预训练过程中，我们将会集中精力解决科技文献中的符号转化问题，希望在大模型时代为科技发展做出贡献。
相比国内外知名商用产品MinerU还很年轻，如果遇到问题或者结果不及预期请到[issue](https://github.com/opendatalab/MinerU/issues)提交问题，同时**附上相关PDF**。
https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
## 快速开始
有多种不同方式可以体验MinerU的效果：
- [在线体验(无需任何安装)](#在线体验)
- [使用CPU快速体验（Windows，Linux，Mac）](#使用cpu快速体验)
### 在线体验
稳定版(经过QA验证的稳定版本)：
[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
测试版(同步dev分支更新，测试新特性)：
[![HuggingFace](https://img.shields.io/badge/Demo_on_HuggingFace-yellow.svg?logo=data:image/png;base64,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
[![ModelScope](https://img.shields.io/badge/Demo_on_ModelScope-purple?logo=data:image/svg+xml;base64,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&labelColor=white)](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
### 使用CPU快速体验
#### 1. 安装magic-pdf
> [!NOTE]
> 最新版本国内镜像源同步可能会有延迟，请耐心等待
```bash
conda create -n MinerU python=3.10
conda activate MinerU
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://mirrors.aliyun.com/pypi/simple
```
#### 2. 下载模型权重文件
详细参考 [如何下载模型文件](docs/how_to_download_models_zh_cn.md)
#### 3. 修改配置文件以进行额外配置
完成[2. 下载模型权重文件](#2-下载模型权重文件)步骤后，脚本会自动生成用户目录下的magic-pdf.json文件，并自动配置默认模型路径。
您可在【用户目录】下找到magic-pdf.json文件。
> [!TIP]
> windows的用户目录为 "C:\\Users\\用户名", linux用户目录为 "/home/用户名", macOS用户目录为 "/Users/用户名"
您可修改该文件中的部分配置实现功能的开关，如表格识别功能：
> [!NOTE]
>如json内没有如下项目，请手动添加需要的项目，并删除注释内容（标准json不支持注释）
```json
{
// other config
"layout-config": {
"model": "layoutlmv3" // 使用doclayout_yolo请修改为“doclayout_yolo"
},
"formula-config": {
"mfd_model": "yolo_v8_mfd",
"mfr_model": "unimernet_small",
"enable": true // 公式识别功能默认是开启的，如果需要关闭请修改此处的值为"false"
},
"table-config": {
"model": "rapid_table", // 默认使用"rapid_table",可以切换为"tablemaster"和"struct_eqtable"
"enable": false, // 表格识别功能默认是关闭的，如果需要开启请修改此处的值为"true"
"max_time": 400
}
}
```
## 使用
### API
处理本地磁盘上的文件
```python
image_writer = DiskReaderWriter(local_image_dir)
image_dir = str(os.path.basename(local_image_dir))
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
处理对象存储上的文件
```python
s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
image_dir = "s3://img_bucket/"
s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
jso_useful_key = {"_pdf_type": "", "model_list": []}
pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
pipe.pipe_classify()
pipe.pipe_analyze()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
```
详细实现可参考
- [demo.py 最简单的处理方式](demo/demo.py)
- [magic_pdf_parse_main.py 能够更清晰看到处理流程](demo/magic_pdf_parse_main.py)
### 部署衍生项目
衍生项目包含项目开发者和社群开发者们基于MinerU的二次开发项目，
例如基于Gradio的应用界面、基于llama的RAG、官网同款web demo、轻量级的多卡负载均衡c/s端等，
这些项目可能会提供更多的功能和更好的用户体验。
具体部署方式请参考 [衍生项目readme](projects/README_zh-CN.md)
### 二次开发
TODO
# TODO
- [x] 基于模型的阅读顺序
- [x] 正文中目录、列表识别
- [x] 表格识别
- [ ] 正文中代码块识别
- [ ] [化学式识别](docs/chemical_knowledge_introduction/introduction.pdf)
- [ ] 几何图形识别
# All Thanks To Our Contributors
<a href="https://github.com/opendatalab/MinerU/graphs/contributors">
<img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
</a>
# License Information
[LICENSE.md](LICENSE.md)
本项目目前采用PyMuPDF以实现高级功能，但因其遵循AGPL协议，可能对某些使用场景构成限制。未来版本迭代中，我们计划探索并替换为许可条款更为宽松的PDF处理库，以提升用户友好度及灵活性。
# Acknowledgments
- [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
- [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO)
- [StructEqTable](https://github.com/UniModal4Reasoning/StructEqTable-Deploy)
- [RapidTable](https://github.com/RapidAI/RapidTable)
- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
- [layoutreader](https://github.com/ppaanngggg/layoutreader)
- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
# Citation
```bibtex
@misc{wang2024mineruopensourcesolutionprecise,
title={MinerU: An Open-Source Solution for Precise Document Content Extraction},
author={Bin Wang and Chao Xu and Xiaomeng Zhao and Linke Ouyang and Fan Wu and Zhiyuan Zhao and Rui Xu and Kaiwen Liu and Yuan Qu and Fukai Shang and Bo Zhang and Liqun Wei and Zhihao Sui and Wei Li and Botian Shi and Yu Qiao and Dahua Lin and Conghui He},
year={2024},
eprint={2409.18839},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2409.18839},
}
@article{he2024opendatalab,
title={Opendatalab: Empowering general artificial intelligence with open datasets},
author={He, Conghui and Li, Wei and Jin, Zhenjiang and Xu, Chao and Wang, Bin and Lin, Dahua},
journal={arXiv preprint arXiv:2407.13773},
year={2024}
}
```
# Star History
<a>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
<source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
<img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
</picture>
</a>
# Magic-doc
[Magic-Doc](https://github.com/InternLM/magic-doc) Fast speed ppt/pptx/doc/docx/pdf extraction tool
# Magic-html
[Magic-HTML](https://github.com/opendatalab/magic-html) Mixed web page extraction tool
# Links
- [LabelU (A Lightweight Multi-modal Data Annotation Tool)](https://github.com/opendatalab/labelU)
- [LabelLLM (An Open-source LLM Dialogue Annotation Platform)](https://github.com/opendatalab/LabelLLM)
- [PDF-Extract-Kit (A Comprehensive Toolkit for High-Quality PDF Content Extraction)](https://github.com/opendatalab/PDF-Extract-Kit)
next_docs/en/_static/image/ReadTheDocs.svg 0 → 100644
View file @ 845a3ff0
<?xml version="1.0" encoding="UTF-8" standalone="no" ?>
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" width="224" height="72" viewBox="-29 -3.67 224 72" xml:space="preserve">
<desc>Created with Fabric.js 5.2.4</desc>
<defs>
</defs>
<rect x="0" y="0" width="100%" height="100%" fill="transparent"></rect>
<g transform="matrix(1 0 0 1 112 36)" id="7a867f58-a908-4f30-a839-fb725512b521" >
<rect style="stroke: none; stroke-width: 1; stroke-dasharray: none; stroke-linecap: butt; stroke-dashoffset: 0; stroke-linejoin: miter; stroke-miterlimit: 4; fill: rgb(255,255,255); fill-rule: nonzero; opacity: 1; visibility: hidden;" vector-effect="non-scaling-stroke" x="-112" y="-36" rx="0" ry="0" width="224" height="72" />
</g>
<g transform="matrix(Infinity NaN NaN Infinity 0 0)" id="29611287-bf1c-4faf-8eb1-df32f6424829" >
</g>
<g transform="matrix(0.07 0 0 0.07 382.02 122.8)" id="60cdd44f-027a-437a-92c4-c8d44c60ef9e" >
<path style="stroke: rgb(0,0,0); stroke-width: 0; stroke-dasharray: none; stroke-linecap: butt; stroke-dashoffset: 0; stroke-linejoin: miter; stroke-miterlimit: 4; fill: rgb(50,50,42); fill-rule: nonzero; opacity: 1;" vector-effect="non-scaling-stroke" transform=" translate(-64, -64)" d="M 57.62 61.68 C 55.919999999999995 61.92 54.75 63.46 55 65.11 C 55.1668510745875 66.32380621250819 56.039448735907676 67.32218371690155 57.22 67.65 C 57.22 67.65 64.69 70.11 77.4 71.16000000000001 C 87.61000000000001 72.01 99.2 70.43 99.2 70.43 C 100.9 70.39 102.23 68.98 102.19 67.28 C 102.17037752125772 66.4652516996782 101.82707564255573 65.69186585376654 101.23597809465886 65.13079230830253 C 100.644880546762 64.56971876283853 99.85466451370849 64.26716220997277 99.03999999999999 64.29 C 98.83999999999999 64.29 98.63999999999999 64.33000000000001 98.42999999999999 64.37 C 98.42999999999999 64.37 87.08999999999999 65.78 77.88 65.02000000000001 C 65.72999999999999 64.05000000000001 59.11 61.83000000000001 59.11 61.83000000000001 C 58.63 61.670000000000016 58.1 61.59000000000001 57.62 61.670000000000016 Z M 57.62 46.46 C 55.919999999999995 46.7 54.75 48.24 55 49.89 C 55.1668510745875 51.10380621250818 56.039448735907676 52.10218371690154 57.22 52.43 C 57.22 52.43 64.69 54.89 77.4 55.94 C 87.61000000000001 56.79 99.2 55.21 99.2 55.21 C 100.9 55.17 102.23 53.76 102.19 52.06 C 102.17037752125772 51.245251699678214 101.82707564255573 50.47186585376654 101.23597809465886 49.91079230830253 C 100.644880546762 49.34971876283853 99.85466451370849 49.047162209972754 99.03999999999999 49.07 C 98.83999999999999 49.07 98.63999999999999 49.11 98.42999999999999 49.15 C 98.42999999999999 49.15 87.08999999999999 50.559999999999995 77.88 49.8 C 65.72999999999999 48.83 59.11 46.61 59.11 46.61 C 58.63 46.45 58.1 46.37 57.62 46.45 Z M 57.62 31.240000000000002 C 55.919999999999995 31.48 54.75 33.02 55 34.67 C 55.1668510745875 35.88380621250818 56.039448735907676 36.882183716901544 57.22 37.21 C 57.22 37.21 64.69 39.67 77.4 40.72 C 87.61000000000001 41.57 99.2 39.99 99.2 39.99 C 100.9 39.95 102.23 38.54 102.19 36.84 C 102.17037752125772 36.025251699678215 101.82707564255573 35.25186585376654 101.23597809465886 34.690792308302534 C 100.644880546762 34.12971876283853 99.85466451370849 33.827162209972755 99.03999999999999 33.85 C 98.83999999999999 33.85 98.63999999999999 33.89 98.42999999999999 33.93 C 98.42999999999999 33.93 87.08999999999999 35.339999999999996 77.88 34.58 C 65.72999999999999 33.61 59.11 31.389999999999997 59.11 31.389999999999997 C 58.63 31.229999999999997 58.1 31.189999999999998 57.62 31.229999999999997 Z M 57.62 16.060000000000002 C 55.919999999999995 16.3 54.75 17.840000000000003 55 19.490000000000002 C 55.1668510745875 20.703806212508187 56.039448735907676 21.702183716901544 57.22 22.03 C 57.22 22.03 64.69 24.490000000000002 77.4 25.54 C 87.61000000000001 26.39 99.2 24.81 99.2 24.81 C 100.9 24.77 102.23 23.36 102.19 21.66 C 102.17037752125772 20.84525169967821 101.82707564255573 20.07186585376654 101.23597809465886 19.510792308302534 C 100.644880546762 18.949718762838526 99.8546645137085 18.64716220997276 99.03999999999999 18.67 C 98.83999999999999 18.67 98.63999999999999 18.71 98.42999999999999 18.75 C 98.42999999999999 18.75 87.08999999999999 20.16 77.88 19.4 C 65.72999999999999 18.43 59.11 16.209999999999997 59.11 16.209999999999997 C 58.637850878541954 16.01924514007714 58.12188500879498 15.963839409097599 57.62 16.049999999999997 Z M 36.31 0 C 20.32 0.12 14.39 5.05 14.39 5.05 L 14.39 124.42 C 14.39 124.42 20.2 119.41 38.93 120.18 C 57.66 120.95000000000002 61.5 127.53 84.50999999999999 127.97000000000001 C 107.52 128.41000000000003 113.28999999999999 124.42000000000002 113.28999999999999 124.42000000000002 L 113.60999999999999 2.750000000000014 C 113.60999999999999 2.750000000000014 103.28 5.7 83.09 5.86 C 62.95 6.01 58.11 0.73 39.62 0.12 C 38.49 0.04 37.4 0 36.31 0 Z M 49.67 7.79 C 49.67 7.79 59.36 10.98 77.24000000000001 11.870000000000001 C 92.38000000000001 12.64 107.52000000000001 10.38 107.52000000000001 10.38 L 107.52000000000001 118.53 C 107.52000000000001 118.53 99.85000000000001 122.57000000000001 80.68 121.19 C 65.82000000000001 120.14 49.480000000000004 114.49 49.480000000000004 114.49 L 49.68000000000001 7.799999999999997 Z M 40.35 10.620000000000001 C 42.050000000000004 10.620000000000001 43.46 11.990000000000002 43.46 13.73 C 43.46 15.469999999999999 42.09 16.84 40.35 16.84 C 40.35 16.84 35.34 16.88 32.28 17.16 C 27.150000000000002 17.68 23.64 19.54 23.64 19.54 C 22.150000000000002 20.349999999999998 20.25 19.74 19.48 18.25 C 18.67 16.76 19.28 14.86 20.77 14.09 C 22.259999999999998 13.32 25.33 11.67 31.67 11.06 C 35.34 10.66 40.35 10.620000000000001 40.35 10.620000000000001 Z M 37.36 25.880000000000003 C 39.06 25.840000000000003 40.35 25.880000000000003 40.35 25.880000000000003 C 42.050000000000004 26.080000000000002 43.260000000000005 27.62 43.050000000000004 29.310000000000002 C 42.88374644848126 30.726609090871516 41.76660909087151 31.843746448481262 40.35 32.010000000000005 C 40.35 32.010000000000005 35.34 32.050000000000004 32.28 32.330000000000005 C 27.150000000000002 32.85000000000001 23.64 34.71000000000001 23.64 34.71000000000001 C 22.150000000000002 35.52000000000001 20.25 34.91000000000001 19.48 33.42000000000001 C 18.67 31.93000000000001 19.28 30.03000000000001 20.77 29.26000000000001 C 20.77 29.26000000000001 25.33 26.84000000000001 31.67 26.230000000000008 C 33.53 25.99000000000001 35.67 25.910000000000007 37.36 25.870000000000008 Z M 40.35 41.06 C 42.050000000000004 41.06 43.46 42.43 43.46 44.17 C 43.46 45.910000000000004 42.09 47.28 40.35 47.28 C 40.35 47.28 35.34 47.24 32.28 47.56 C 27.150000000000002 48.080000000000005 23.64 49.940000000000005 23.64 49.940000000000005 C 22.150000000000002 50.75000000000001 20.25 50.14000000000001 19.48 48.650000000000006 C 18.67 47.160000000000004 19.28 45.260000000000005 20.77 44.49000000000001 C 20.77 44.49000000000001 25.33 42.07000000000001 31.67 41.46000000000001 C 35.34 41.02000000000001 40.35 41.06000000000001 40.35 41.06000000000001 Z" stroke-linecap="round" />
</g>
<g transform="matrix(0.07 0 0 0.07 396.05 123.14)" style="" id="eb0df536-c517-4781-a7c0-3f84cd77c272" >
<text xml:space="preserve" font-family="Lato" font-size="40" font-style="normal" font-weight="400" style="stroke: none; stroke-width: 1; stroke-dasharray: none; stroke-linecap: butt; stroke-dashoffset: 0; stroke-linejoin: miter; stroke-miterlimit: 4; fill: rgb(0,0,0); fill-rule: nonzero; opacity: 1; white-space: pre;" ><tspan x="-130" y="12.57" >Read The Docs</tspan></text>
</g>
<g transform="matrix(0.28 0 0 0.28 27.88 36)" id="7b9eddb9-1652-4040-9437-2ab90652d624" >
<path style="stroke: rgb(0,0,0); stroke-width: 0; stroke-dasharray: none; stroke-linecap: butt; stroke-dashoffset: 0; stroke-linejoin: miter; stroke-miterlimit: 4; fill: rgb(50,50,42); fill-rule: nonzero; opacity: 1;" vector-effect="non-scaling-stroke" transform=" translate(-64, -64)" d="M 57.62 61.68 C 55.919999999999995 61.92 54.75 63.46 55 65.11 C 55.1668510745875 66.32380621250819 56.039448735907676 67.32218371690155 57.22 67.65 C 57.22 67.65 64.69 70.11 77.4 71.16000000000001 C 87.61000000000001 72.01 99.2 70.43 99.2 70.43 C 100.9 70.39 102.23 68.98 102.19 67.28 C 102.17037752125772 66.4652516996782 101.82707564255573 65.69186585376654 101.23597809465886 65.13079230830253 C 100.644880546762 64.56971876283853 99.85466451370849 64.26716220997277 99.03999999999999 64.29 C 98.83999999999999 64.29 98.63999999999999 64.33000000000001 98.42999999999999 64.37 C 98.42999999999999 64.37 87.08999999999999 65.78 77.88 65.02000000000001 C 65.72999999999999 64.05000000000001 59.11 61.83000000000001 59.11 61.83000000000001 C 58.63 61.670000000000016 58.1 61.59000000000001 57.62 61.670000000000016 Z M 57.62 46.46 C 55.919999999999995 46.7 54.75 48.24 55 49.89 C 55.1668510745875 51.10380621250818 56.039448735907676 52.10218371690154 57.22 52.43 C 57.22 52.43 64.69 54.89 77.4 55.94 C 87.61000000000001 56.79 99.2 55.21 99.2 55.21 C 100.9 55.17 102.23 53.76 102.19 52.06 C 102.17037752125772 51.245251699678214 101.82707564255573 50.47186585376654 101.23597809465886 49.91079230830253 C 100.644880546762 49.34971876283853 99.85466451370849 49.047162209972754 99.03999999999999 49.07 C 98.83999999999999 49.07 98.63999999999999 49.11 98.42999999999999 49.15 C 98.42999999999999 49.15 87.08999999999999 50.559999999999995 77.88 49.8 C 65.72999999999999 48.83 59.11 46.61 59.11 46.61 C 58.63 46.45 58.1 46.37 57.62 46.45 Z M 57.62 31.240000000000002 C 55.919999999999995 31.48 54.75 33.02 55 34.67 C 55.1668510745875 35.88380621250818 56.039448735907676 36.882183716901544 57.22 37.21 C 57.22 37.21 64.69 39.67 77.4 40.72 C 87.61000000000001 41.57 99.2 39.99 99.2 39.99 C 100.9 39.95 102.23 38.54 102.19 36.84 C 102.17037752125772 36.025251699678215 101.82707564255573 35.25186585376654 101.23597809465886 34.690792308302534 C 100.644880546762 34.12971876283853 99.85466451370849 33.827162209972755 99.03999999999999 33.85 C 98.83999999999999 33.85 98.63999999999999 33.89 98.42999999999999 33.93 C 98.42999999999999 33.93 87.08999999999999 35.339999999999996 77.88 34.58 C 65.72999999999999 33.61 59.11 31.389999999999997 59.11 31.389999999999997 C 58.63 31.229999999999997 58.1 31.189999999999998 57.62 31.229999999999997 Z M 57.62 16.060000000000002 C 55.919999999999995 16.3 54.75 17.840000000000003 55 19.490000000000002 C 55.1668510745875 20.703806212508187 56.039448735907676 21.702183716901544 57.22 22.03 C 57.22 22.03 64.69 24.490000000000002 77.4 25.54 C 87.61000000000001 26.39 99.2 24.81 99.2 24.81 C 100.9 24.77 102.23 23.36 102.19 21.66 C 102.17037752125772 20.84525169967821 101.82707564255573 20.07186585376654 101.23597809465886 19.510792308302534 C 100.644880546762 18.949718762838526 99.8546645137085 18.64716220997276 99.03999999999999 18.67 C 98.83999999999999 18.67 98.63999999999999 18.71 98.42999999999999 18.75 C 98.42999999999999 18.75 87.08999999999999 20.16 77.88 19.4 C 65.72999999999999 18.43 59.11 16.209999999999997 59.11 16.209999999999997 C 58.637850878541954 16.01924514007714 58.12188500879498 15.963839409097599 57.62 16.049999999999997 Z M 36.31 0 C 20.32 0.12 14.39 5.05 14.39 5.05 L 14.39 124.42 C 14.39 124.42 20.2 119.41 38.93 120.18 C 57.66 120.95000000000002 61.5 127.53 84.50999999999999 127.97000000000001 C 107.52 128.41000000000003 113.28999999999999 124.42000000000002 113.28999999999999 124.42000000000002 L 113.60999999999999 2.750000000000014 C 113.60999999999999 2.750000000000014 103.28 5.7 83.09 5.86 C 62.95 6.01 58.11 0.73 39.62 0.12 C 38.49 0.04 37.4 0 36.31 0 Z M 49.67 7.79 C 49.67 7.79 59.36 10.98 77.24000000000001 11.870000000000001 C 92.38000000000001 12.64 107.52000000000001 10.38 107.52000000000001 10.38 L 107.52000000000001 118.53 C 107.52000000000001 118.53 99.85000000000001 122.57000000000001 80.68 121.19 C 65.82000000000001 120.14 49.480000000000004 114.49 49.480000000000004 114.49 L 49.68000000000001 7.799999999999997 Z M 40.35 10.620000000000001 C 42.050000000000004 10.620000000000001 43.46 11.990000000000002 43.46 13.73 C 43.46 15.469999999999999 42.09 16.84 40.35 16.84 C 40.35 16.84 35.34 16.88 32.28 17.16 C 27.150000000000002 17.68 23.64 19.54 23.64 19.54 C 22.150000000000002 20.349999999999998 20.25 19.74 19.48 18.25 C 18.67 16.76 19.28 14.86 20.77 14.09 C 22.259999999999998 13.32 25.33 11.67 31.67 11.06 C 35.34 10.66 40.35 10.620000000000001 40.35 10.620000000000001 Z M 37.36 25.880000000000003 C 39.06 25.840000000000003 40.35 25.880000000000003 40.35 25.880000000000003 C 42.050000000000004 26.080000000000002 43.260000000000005 27.62 43.050000000000004 29.310000000000002 C 42.88374644848126 30.726609090871516 41.76660909087151 31.843746448481262 40.35 32.010000000000005 C 40.35 32.010000000000005 35.34 32.050000000000004 32.28 32.330000000000005 C 27.150000000000002 32.85000000000001 23.64 34.71000000000001 23.64 34.71000000000001 C 22.150000000000002 35.52000000000001 20.25 34.91000000000001 19.48 33.42000000000001 C 18.67 31.93000000000001 19.28 30.03000000000001 20.77 29.26000000000001 C 20.77 29.26000000000001 25.33 26.84000000000001 31.67 26.230000000000008 C 33.53 25.99000000000001 35.67 25.910000000000007 37.36 25.870000000000008 Z M 40.35 41.06 C 42.050000000000004 41.06 43.46 42.43 43.46 44.17 C 43.46 45.910000000000004 42.09 47.28 40.35 47.28 C 40.35 47.28 35.34 47.24 32.28 47.56 C 27.150000000000002 48.080000000000005 23.64 49.940000000000005 23.64 49.940000000000005 C 22.150000000000002 50.75000000000001 20.25 50.14000000000001 19.48 48.650000000000006 C 18.67 47.160000000000004 19.28 45.260000000000005 20.77 44.49000000000001 C 20.77 44.49000000000001 25.33 42.07000000000001 31.67 41.46000000000001 C 35.34 41.02000000000001 40.35 41.06000000000001 40.35 41.06000000000001 Z" stroke-linecap="round" />
</g>
<g transform="matrix(0.9 0 0 0.9 94 36)" style="" id="385bde16-f9fa-4222-bfea-1d5d5efcf730" >
<text xml:space="preserve" font-family="Lato" font-size="15" font-style="normal" font-weight="100" style="stroke: none; stroke-width: 1; stroke-dasharray: none; stroke-linecap: butt; stroke-dashoffset: 0; stroke-linejoin: miter; stroke-miterlimit: 4; fill: rgb(0,0,0); fill-rule: nonzero; opacity: 1; white-space: pre;" ><tspan x="-48.68" y="4.71" >Read The Docs</tspan></text>
</g>
</svg>
\ No newline at end of file
next_docs/en/additional_notes/changelog.rst deleted 100644 → 0
View file @ d0558abb
Changelog
=========
- 2024/09/27 Version 0.8.1 released, Fixed some bugs, and providing a
`localized deployment version <projects/web_demo/README.md>`__ of the
`online
demo <https://opendatalab.com/OpenSourceTools/Extractor/PDF/>`__ and
the `front-end interface <projects/web/README.md>`__.
- 2024/09/09: Version 0.8.0 released, supporting fast deployment with
Dockerfile, and launching demos on Huggingface and Modelscope.
- 2024/08/30: Version 0.7.1 released, add paddle tablemaster table
recognition option
- 2024/08/09: Version 0.7.0b1 released, simplified installation
process, added table recognition functionality
- 2024/08/01: Version 0.6.2b1 released, optimized dependency conflict
issues and installation documentation
- 2024/07/05: Initial open-source release
.. warning::
fix ``localized deployment version`` and ``front-end interface``
next_docs/en/additional_notes/faq.rst
View file @ 845a3ff0
......@@ -74,3 +74,15 @@ CUDA version used by Paddle needs to be upgraded.
pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu123/
Reference: https://github.com/opendatalab/MinerU/issues/558
7. On some Linux servers, the program immediately reports an error ``Illegal instruction (core dumped)``
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
This might be because the server's CPU does not support the AVX/AVX2
instruction set, or the CPU itself supports it but has been disabled by
the system administrator. You can try contacting the system
administrator to remove the restriction or change to a different server.
References: https://github.com/opendatalab/MinerU/issues/591 ,
https://github.com/opendatalab/MinerU/issues/736
next_docs/en/additional_notes/known_issues.rst
View file @ 845a3ff0
Known Issues
============
- Reading order is based on the model’s sorting of text distribution in
space, which may become disordered under extremely complex layouts.
- Reading order is determined by the model based on the spatial
distribution of readable content, and may be out of order in some
areas under extremely complex layouts.
- Vertical text is not supported.
- Tables of contents and lists are recognized through rules; a few
uncommon list formats may not be identified.
- Only one level of headings is supported; hierarchical heading levels
are currently not supported.
- Tables of contents and lists are recognized through rules, and some
uncommon list formats may not be recognized.
- Only one level of headings is supported; hierarchical headings are
not currently supported.
- Code blocks are not yet supported in the layout model.
- Comic books, art books, elementary school textbooks, and exercise
books are not well-parsed yet
- Enabling OCR may produce better results in PDFs with a high density
of formulas
- If you are processing PDFs with a large number of formulas, it is
strongly recommended to enable the OCR function. When using PyMuPDF
to extract text, overlapping text lines can occur, leading to
inaccurate formula insertion positions.
- Comic books, art albums, primary school textbooks, and exercises
cannot be parsed well.
- Table recognition may result in row/column recognition errors in
complex tables.
- OCR recognition may produce inaccurate characters in PDFs of
lesser-known languages (e.g., diacritical marks in Latin script,
easily confused characters in Arabic script).
- Some formulas may not render correctly in Markdown.
\ No newline at end of file
next_docs/en/api.rst
View file @ 845a3ff0
......@@ -7,4 +7,3 @@
api/read_api
api/schemas
api/io
api/classes
\ No newline at end of file
next_docs/en/api/classes.rst deleted 100644 → 0
View file @ d0558abb
Class Hierarchy
===============
.. inheritance-diagram:: magic_pdf.data.io.base magic_pdf.data.io.http magic_pdf.data.io.s3
:parts: 2
.. inheritance-diagram:: magic_pdf.data.dataset
:parts: 2
.. inheritance-diagram:: magic_pdf.data.data_reader_writer.base magic_pdf.data.data_reader_writer.filebase magic_pdf.data.data_reader_writer.multi_bucket_s3
:parts: 2
next_docs/en/conf.py
View file @ 845a3ff0
......@@ -95,7 +95,7 @@ language = 'en'
html_theme = 'sphinx_book_theme'
html_logo = '_static/image/logo.png'
html_theme_options = {
'path_to_docs': 'docs/en',
'path_to_docs': 'next_docs/en',
'repository_url': 'https://github.com/opendatalab/MinerU',
'use_repository_button': True,
}
......
next_docs/en/index.rst
View file @ 845a3ff0
......@@ -46,20 +46,29 @@ the relevant PDF**.
Key Features
------------
- Removes elements such as headers, footers, footnotes, and page
numbers while maintaining semantic continuity
- Outputs text in a human-readable order from multi-column documents
- Retains the original structure of the document, including titles,
paragraphs, and lists
- Extracts images, image captions, tables, and table captions
- Automatically recognizes formulas in the document and converts them
to LaTeX
- Automatically recognizes tables in the document and converts them to
LaTeX
- Automatically detects and enables OCR for corrupted PDFs
- Supports both CPU and GPU environments
- Supports Windows, Linux, and Mac platforms
- 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.
User Guide
-------------
......@@ -91,14 +100,6 @@ Additional Notes
additional_notes/known_issues
additional_notes/faq
additional_notes/changelog
additional_notes/glossary
Projects
---------
.. toctree::
:maxdepth: 1
:caption: Projects
projects
\ No newline at end of file
next_docs/en/projects.rst deleted 100644 → 0
View file @ d0558abb
llama_index_rag
===============
gradio_app
============
other projects
===============
\ No newline at end of file
next_docs/en/user_guide/data/data_reader_writer.rst
View file @ 845a3ff0
......@@ -87,6 +87,8 @@ Read Examples
.. code:: python
from magic_pdf.data.data_reader_writer import *
# file based related
file_based_reader1 = FileBasedDataReader('')
......@@ -142,6 +144,8 @@ Write Examples
.. code:: python
from magic_pdf.data.data_reader_writer import *
# file based related
file_based_writer1 = FileBasedDataWriter('')
......@@ -201,4 +205,4 @@ Write Examples
s3_writer1.write('s3://test_bucket/efg', '123'.encode())
Check :doc:`../../api/classes` for more intuitions or check :doc:`../../api/data_reader_writer` for more details
Check :doc:`../../api/data_reader_writer` for more details
next_docs/en/user_guide/data/dataset.rst
View file @ 845a3ff0
......@@ -36,5 +36,5 @@ Extract chars via third-party library, currently we use ``pymupdf``.
Check :doc:`../../api/classes` for more intuitions or check :doc:`../../api/dataset` for more details
Check :doc:`../../api/dataset` for more details
next_docs/en/user_guide/data/io.rst
View file @ 845a3ff0
......@@ -21,5 +21,5 @@ if MinerU have not provide the suitable classes. It is easy to implement new cla
def write(self, path: str, data: bytes) -> None:
pass
Check :doc:`../../api/classes` for more intuitions or check :doc:`../../api/io` for more details
Check :doc:`../../api/io` for more details
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