magic-pdf 0.10.5__py3-none-any.whl → 1.0.0__py3-none-any.whl

magic_pdf/tools/common.py

@@ -1,5 +1,3 @@
-import copy
-import json as json_parse
 import os
 
 import click
@@ -7,13 +5,13 @@ import fitz
 from loguru import logger
 
 import magic_pdf.model as model_config
+from magic_pdf.config.enums import SupportedPdfParseMethod
 from magic_pdf.config.make_content_config import DropMode, MakeMode
 from magic_pdf.data.data_reader_writer import FileBasedDataWriter
-from magic_pdf.libs.draw_bbox import (draw_layout_bbox, draw_line_sort_bbox,
-                                      draw_model_bbox, draw_span_bbox)
-from magic_pdf.pipe.OCRPipe import OCRPipe
-from magic_pdf.pipe.TXTPipe import TXTPipe
-from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.data.dataset import PymuDocDataset
+from magic_pdf.libs.draw_bbox import draw_char_bbox
+from magic_pdf.model.doc_analyze_by_custom_model import doc_analyze
+from magic_pdf.operators.models import InferenceResult
 
 # from io import BytesIO
 # from pypdf import PdfReader, PdfWriter
@@ -56,7 +54,11 @@ def prepare_env(output_dir, pdf_file_name, method):
 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
+    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
@@ -82,6 +84,7 @@ def do_parse(
     f_make_md_mode=MakeMode.MM_MD,
     f_draw_model_bbox=False,
     f_draw_line_sort_bbox=False,
+    f_draw_char_bbox=False,
     start_page_id=0,
     end_page_id=None,
     lang=None,
@@ -93,79 +96,135 @@ def do_parse(
         logger.warning('debug mode is on')
         f_draw_model_bbox = True
         f_draw_line_sort_bbox = True
+        # f_draw_char_bbox = True
 
-    if lang == "":
-        lang = None
+    pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf(
+        pdf_bytes, start_page_id, end_page_id
+    )
 
-    pdf_bytes = convert_pdf_bytes_to_bytes_by_pymupdf(pdf_bytes, start_page_id, end_page_id)
+    local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name, parse_method)
 
-    orig_model_list = copy.deepcopy(model_list)
-    local_image_dir, local_md_dir = prepare_env(output_dir, pdf_file_name,
-                                                parse_method)
-
-    image_writer, md_writer = FileBasedDataWriter(
-        local_image_dir), FileBasedDataWriter(local_md_dir)
+    image_writer, md_writer = FileBasedDataWriter(local_image_dir), FileBasedDataWriter(
+        local_md_dir
+    )
     image_dir = str(os.path.basename(local_image_dir))
 
-    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,
-                       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,
-                       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,
-                       layout_model=layout_model, formula_enable=formula_enable, table_enable=table_enable)
-    else:
-        logger.error('unknown parse method')
-        exit(1)
-
-    pipe.pipe_classify()
+    ds = PymuDocDataset(pdf_bytes, lang=lang)
 
     if len(model_list) == 0:
         if model_config.__use_inside_model__:
-            pipe.pipe_analyze()
-            orig_model_list = copy.deepcopy(pipe.model_list)
+            if parse_method == 'auto':
+                if ds.classify() == SupportedPdfParseMethod.TXT:
+                    infer_result = ds.apply(
+                        doc_analyze,
+                        ocr=False,
+                        lang=ds._lang,
+                        layout_model=layout_model,
+                        formula_enable=formula_enable,
+                        table_enable=table_enable,
+                    )
+                    pipe_result = infer_result.pipe_txt_mode(
+                        image_writer, debug_mode=True, lang=ds._lang
+                    )
+                else:
+                    infer_result = ds.apply(
+                        doc_analyze,
+                        ocr=True,
+                        lang=ds._lang,
+                        layout_model=layout_model,
+                        formula_enable=formula_enable,
+                        table_enable=table_enable,
+                    )
+                    pipe_result = infer_result.pipe_ocr_mode(
+                        image_writer, debug_mode=True, lang=ds._lang
+                    )
+
+            elif parse_method == 'txt':
+                infer_result = ds.apply(
+                    doc_analyze,
+                    ocr=False,
+                    lang=ds._lang,
+                    layout_model=layout_model,
+                    formula_enable=formula_enable,
+                    table_enable=table_enable,
+                )
+                pipe_result = infer_result.pipe_txt_mode(
+                    image_writer, debug_mode=True, lang=ds._lang
+                )
+            elif parse_method == 'ocr':
+                infer_result = ds.apply(
+                    doc_analyze,
+                    ocr=True,
+                    lang=ds._lang,
+                    layout_model=layout_model,
+                    formula_enable=formula_enable,
+                    table_enable=table_enable,
+                )
+                pipe_result = infer_result.pipe_ocr_mode(
+                    image_writer, debug_mode=True, lang=ds._lang
+                )
+            else:
+                logger.error('unknown parse method')
+                exit(1)
         else:
             logger.error('need model list input')
             exit(2)
+    else:
+
+        infer_result = InferenceResult(model_list, ds)
+        if parse_method == 'ocr':
+            pipe_result = infer_result.pipe_ocr_mode(
+                image_writer, debug_mode=True, lang=ds._lang
+            )
+        elif parse_method == 'txt':
+            pipe_result = infer_result.pipe_txt_mode(
+                image_writer, debug_mode=True, lang=ds._lang
+            )
+        else:
+            if ds.classify() == SupportedPdfParseMethod.TXT:
+                pipe_result = infer_result.pipe_txt_mode(
+                        image_writer, debug_mode=True, lang=ds._lang
+                    )
+            else:
+                pipe_result = infer_result.pipe_ocr_mode(
+                        image_writer, debug_mode=True, lang=ds._lang
+                    )
+
+
+    if f_draw_model_bbox:
+        infer_result.draw_model(
+            os.path.join(local_md_dir, f'{pdf_file_name}_model.pdf')
+        )
 
-    pipe.pipe_parse()
-    pdf_info = pipe.pdf_mid_data['pdf_info']
     if f_draw_layout_bbox:
-        draw_layout_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
+        pipe_result.draw_layout(
+            os.path.join(local_md_dir, f'{pdf_file_name}_layout.pdf')
+        )
     if f_draw_span_bbox:
-        draw_span_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
-    if f_draw_model_bbox:
-        draw_model_bbox(copy.deepcopy(orig_model_list), pdf_bytes, local_md_dir, pdf_file_name)
+        pipe_result.draw_span(os.path.join(local_md_dir, f'{pdf_file_name}_spans.pdf'))
+
     if f_draw_line_sort_bbox:
-        draw_line_sort_bbox(pdf_info, pdf_bytes, local_md_dir, pdf_file_name)
+        pipe_result.draw_line_sort(
+            os.path.join(local_md_dir, f'{pdf_file_name}_line_sort.pdf')
+        )
+
+    if f_draw_char_bbox:
+        draw_char_bbox(pdf_bytes, local_md_dir, f'{pdf_file_name}_char_bbox.pdf')
 
-    md_content = pipe.pipe_mk_markdown(image_dir, drop_mode=DropMode.NONE, md_make_mode=f_make_md_mode)
     if f_dump_md:
-        md_writer.write_string(
+        pipe_result.dump_md(
+            md_writer,
             f'{pdf_file_name}.md',
-            md_content
+            image_dir,
+            drop_mode=DropMode.NONE,
+            md_make_mode=f_make_md_mode,
         )
 
     if f_dump_middle_json:
-        md_writer.write_string(
-            f'{pdf_file_name}_middle.json',
-            json_parse.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4)
-        )
+        pipe_result.dump_middle_json(md_writer, f'{pdf_file_name}_middle.json')
 
     if f_dump_model_json:
-        md_writer.write_string(
-            f'{pdf_file_name}_model.json',
-            json_parse.dumps(orig_model_list, ensure_ascii=False, indent=4)
-        )
+        infer_result.dump_model(md_writer, f'{pdf_file_name}_model.json')
 
     if f_dump_orig_pdf:
         md_writer.write(
@@ -173,11 +232,11 @@ def do_parse(
             pdf_bytes,
         )
 
-    content_list = pipe.pipe_mk_uni_format(image_dir, drop_mode=DropMode.NONE)
     if f_dump_content_list:
-        md_writer.write_string(
+        pipe_result.dump_content_list(
+            md_writer,
             f'{pdf_file_name}_content_list.json',
-            json_parse.dumps(content_list, ensure_ascii=False, indent=4)
+            image_dir
         )
 
     logger.info(f'local output dir is {local_md_dir}')

magic_pdf/utils/office_to_pdf.py

@@ -0,0 +1,29 @@
+import os
+import subprocess
+from pathlib import Path
+
+
+class ConvertToPdfError(Exception):
+    def __init__(self, msg):
+        self.msg = msg
+        super().__init__(self.msg)
+
+
+def convert_file_to_pdf(input_path, output_dir):
+    if not os.path.isfile(input_path):
+        raise FileNotFoundError(f"The input file {input_path} does not exist.")
+
+    os.makedirs(output_dir, exist_ok=True)
+    
+    cmd = [
+        'soffice',
+        '--headless',
+        '--convert-to', 'pdf',
+        '--outdir', str(output_dir),
+        str(input_path)
+    ]
+    
+    process = subprocess.run(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    
+    if process.returncode != 0:
+        raise ConvertToPdfError(process.stderr.decode())

{magic_pdf-0.10.5.dist-info → magic_pdf-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.10.5
+Version: 1.0.0
 Summary: A practical tool for converting PDF to Markdown
 Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
@@ -9,25 +9,30 @@ License-File: LICENSE.md
 Requires-Dist: boto3>=1.28.43
 Requires-Dist: Brotli>=1.1.0
 Requires-Dist: click>=8.1.7
-Requires-Dist: fast-langdetect==0.2.0
+Requires-Dist: fast-langdetect>=0.2.3
 Requires-Dist: loguru>=0.6.0
 Requires-Dist: numpy<2.0.0,>=1.21.6
-Requires-Dist: pydantic<2.8.0,>=2.7.2
+Requires-Dist: pydantic>=2.7.2
 Requires-Dist: PyMuPDF>=1.24.9
 Requires-Dist: scikit-learn>=1.0.2
-Requires-Dist: torch<=2.3.1,>=2.2.2
+Requires-Dist: torch>=2.2.2
 Requires-Dist: transformers
+Requires-Dist: pdfminer.six==20231228
 Provides-Extra: full
-Requires-Dist: unimernet==0.2.1; extra == "full"
-Requires-Dist: ultralytics; extra == "full"
+Requires-Dist: unimernet==0.2.3; extra == "full"
+Requires-Dist: torch<=2.3.1,>=2.2.2; extra == "full"
+Requires-Dist: torchvision<=0.18.1,>=0.17.2; extra == "full"
+Requires-Dist: ultralytics>=8.3.48; extra == "full"
 Requires-Dist: paddleocr==2.7.3; extra == "full"
 Requires-Dist: struct-eqtable==0.3.2; extra == "full"
 Requires-Dist: einops; extra == "full"
 Requires-Dist: accelerate; extra == "full"
 Requires-Dist: doclayout-yolo==0.0.2; extra == "full"
 Requires-Dist: rapidocr-paddle; extra == "full"
-Requires-Dist: rapid-table; extra == "full"
+Requires-Dist: rapidocr-onnxruntime; extra == "full"
+Requires-Dist: rapid-table==0.3.0; extra == "full"
 Requires-Dist: PyYAML; extra == "full"
+Requires-Dist: openai; extra == "full"
 Requires-Dist: detectron2; extra == "full"
 Requires-Dist: paddlepaddle==3.0.0b1; platform_system == "Linux" and extra == "full"
 Requires-Dist: matplotlib; (platform_system == "Linux" or platform_system == "Darwin") and extra == "full"
@@ -56,7 +61,7 @@ Requires-Dist: albumentations<=1.4.20; extra == "old-linux"
 [![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,PHN2ZyB3aWR0aD0iMzAiIGhlaWdodD0iMzAiIHhtbG5zPSJodHRwOi8vd3d3LnczLm9yZy8yMDAwL3N2ZyIgZmlsbD0ibm9uZSI+CiA8ZGVmcz4KICA8bGluZWFyR3JhZGllbnQgeTI9IjAuNTMzNjciIHgyPSIxLjAwMDQiIHkxPSIwLjI5MjE5IiB4MT0iLTAuMTEyNjgiIGlkPSJhIj4KICAgPHN0b3Agc3RvcC1jb2xvcj0iIzE1NDNGRSIvPgogICA8c3RvcCBzdG9wLWNvbG9yPSIjOEM0NkZGIiBvZmZzZXQ9IjEiLz4KICA8L2xpbmVhckdyYWRpZW50PgogIDxsaW5lYXJHcmFkaWVudCB5Mj0iMC41OTc1NyIgeDI9IjEuMDExMzciIHkxPSIwLjExMDIzIiB4MT0iLTAuMDg0NzQiIGlkPSJiIj4KICAgPHN0b3Agc3RvcC1jb2xvcj0iIzE1NDNGRSIvPgogICA8c3RvcCBzdG9wLWNvbG9yPSIjOEM0NkZGIiBvZmZzZXQ9IjEiLz4KICA8L2xpbmVhckdyYWRpZW50PgogPC9kZWZzPgogPGc+CiAgPHRpdGxlPkxheWVyIDE8L3RpdGxlPgogIDxwYXRoIGlkPSJzdmdfMSIgZmlsbD0idXJsKCNhKSIgZD0ibTEuNjIzLDEyLjA2N2EwLjQ4NCwwLjQ4NCAwIDAgMSAwLjA3LC0wLjM4NGw1LjMxLC03Ljg5NWMwLjA2OCwtMC4xIDAuMTcsLTAuMTcyIDAuMjg4LC0wLjJsMTQuMzc3LC0zLjQ3NGEwLjQ4NCwwLjQ4NCAwIDAgMSAwLjU4NCwwLjM1N2wzLjY2MiwxNS4xNTJjMS40NzcsNi4xMTQgLTIuMjgxLDEyLjI2NyAtOC4zOTQsMTMuNzQ1Yy02LjExNCwxLjQ3NyAtMTIuMjY3LC0yLjI4MSAtMTMuNzQ1LC04LjM5NWwtMi4xNTIsLTguOTA2eiIgb3BhY2l0eT0iMC40Ii8+CiAgPHBhdGggaWQ9InN2Z18yIiBmaWxsPSJ1cmwoI2IpIiBkPSJtNS44MjYsOC42NzNjMCwtMC4xMzYgMC4wNTcsLTAuMjY2IDAuMTU3LC0wLjM1OGw3LjAxNywtNi40MjVhMC40ODQsMC40ODQgMCAwIDEgMC4zMjcsLTAuMTI3bDE0Ljc5LDBjMC4yNjgsMCAwLjQ4NSwwLjIxNiAwLjQ4NSwwLjQ4NGwwLDE1LjU4OWMwLDYuMjkgLTUuMDk5LDExLjM4OCAtMTEuMzg4LDExLjM4OGMtNi4yOSwwIC0xMS4zODgsLTUuMDk5IC0xMS4zODgsLTExLjM4OGwwLC05LjE2M3oiLz4KICA8cGF0aCBpZD0ic3ZnXzMiIGZpbGw9IiM1RDc2RkYiIGQ9Im0xMi4zMzEsOC43NTNsLTYuMzgzLC0wLjM5OGw3LjEyMiwtNi41MmwwLjI5OSw1Ljg5MmEwLjk3OCwwLjk3OCAwIDAgMSAtMS4wMzgsMS4wMjZ6Ii8+CiAgPHBhdGggaWQ9InN2Z180IiBmaWxsPSIjMDAyOEZEIiBkPSJtMjAuNDE2LDE1LjAyMmwwLDEuNzExYTIuNDA0LDIuNDA0IDAgMCAxIC00LjgwOCwwbDAsLTQuMjc4bC0yLjgxLDBsMCw0LjY4NmE1LjIxNSw1LjIxNSAwIDEgMCAxMC40MywwbDAsLTQuNjg2bDAsMi41NjdsLTIuODEyLDB6IiBjbGlwLXJ1bGU9ImV2ZW5vZGQiIGZpbGwtcnVsZT0iZXZlbm9kZCIvPgogIDxwYXRoIGlkPSJzdmdfNSIgZmlsbD0iIzAwMjhGRCIgZD0ibTIzLjIyOCwxMy44ODFsMS4xNCwwbDAsMS4xNDFsLTEuMTQsMGwwLC0xLjE0bDAsLTAuMDAxem0tMi44MTIsLTAuNjkybDEuODM0LDBsMCwxLjgzM2wtMS44MzQsMGwwLC0xLjgzMmwwLC0wLjAwMXptMS44MzQsLTAuOTc5bDAuOTc4LDBsMCwwLjk3OWwtMC45NzgsMGwwLC0wLjk3OGwwLC0wLjAwMXptMS41NDgsLTEuNjI5bDAuNjExLDBsMCwwLjYxMWwtMC42MTEsMGwwLC0wLjYxMXoiLz4KICA8cGF0aCBpZD0ic3ZnXzYiIGZpbGw9IiNmZmYiIGQ9Im0yMC4wODYsMTQuOTEybDAsMS43MTFhMi40MDQsMi40MDQgMCAxIDEgLTQuODA3LDBsMCwtNC4yNzhsLTIuODEyLDBsMCw0LjY4NmE1LjIxNSw1LjIxNSAwIDAgMCAxMC40MywwbDAsLTQuNjg2bDAsMi41NjdsLTIuODEsMGwtMC4wMDEsMHoiIGNsaXAtcnVsZT0iZXZlbm9kZCIgZmlsbC1ydWxlPSJldmVub2RkIi8+CiAgPHBhdGggaWQ9InN2Z183IiBmaWxsPSIjZmZmIiBkPSJtMjIuODk4LDEzLjc3MWwxLjE0LDBsMCwxLjE0MWwtMS4xNCwwbDAsLTEuMTRsMCwtMC4wMDF6bS0yLjgxMiwtMC42OTJsMS44MzQsMGwwLDEuODMzbC0xLjgzNCwwbDAsLTEuODMybDAsLTAuMDAxem0xLjgzNCwtMC45NzlsMC45NzgsMGwwLDAuOTc5bC0wLjk3OCwwbDAsLTAuOTc5em0xLjU0OCwtMS42MjlsMC42MTEsMGwwLDAuNjExbC0wLjYxLDBsMCwtMC42MWwtMC4wMDEsLTAuMDAxeiIvPgogPC9nPgo8L3N2Zz4=&labelColor=white)](https://opendatalab.com/OpenSourceTools/Extractor/PDF)
+[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://mineru.org.cn/OpenSourceTools/Extractor?source=github)
 [![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)
@@ -73,6 +78,11 @@ Requires-Dist: albumentations<=1.4.20; extra == "old-linux"
 
 <p align="center">
 <a href="https://github.com/opendatalab/PDF-Extract-Kit">PDF-Extract-Kit: High-Quality PDF Extraction Toolkit</a>🔥🔥🔥
+<br>
+<br>
+<a href="https://mineru.org.cn/client?source=github">
+Easier to use: Just grab MinerU Desktop. No coding, no login, just a simple interface and smooth interactions. Enjoy it without any fuss!</a>🚀🚀🚀
+
 </p>
 
 <!-- join us -->
@@ -84,6 +94,15 @@ Requires-Dist: albumentations<=1.4.20; extra == "old-linux"
 </div>
 
 # Changelog
+- 2025/01/10 1.0.0 released. This is our first official release, where we have introduced a completely new API interface and enhanced compatibility through extensive refactoring, as well as a brand new automatic language identification feature:
+  - New API Interface
+    - For the data-side API, we have introduced the Dataset class, designed to provide a robust and flexible data processing framework. This framework currently supports a variety of document formats, including images (.jpg and .png), PDFs, Word documents (.doc and .docx), and PowerPoint presentations (.ppt and .pptx). It ensures effective support for data processing tasks ranging from simple to complex.
+    - For the user-side API, we have meticulously designed the MinerU processing workflow as a series of composable Stages. Each Stage represents a specific processing step, allowing users to define new Stages according to their needs and creatively combine these stages to customize their data processing workflows.
+  - Enhanced Compatibility
+    - By optimizing the dependency environment and configuration items, we ensure stable and efficient operation on ARM architecture Linux systems.
+    - We have deeply integrated with Huawei Ascend NPU acceleration, providing autonomous and controllable high-performance computing capabilities. This supports the localization and development of AI application platforms in China. [Ascend NPU Acceleration](docs/README_Ascend_NPU_Acceleration_zh_CN.md)
+  - Automatic Language Identification
+    - By introducing a new language recognition model, setting the `lang` configuration to `auto` during document parsing will automatically select the appropriate OCR language model, improving the accuracy of scanned document parsing.
 - 2024/11/22 0.10.0 released. Introducing hybrid OCR text extraction capabilities,
   - Significantly improved parsing performance in complex text distribution scenarios such as dense formulas, irregular span regions, and text represented by images.
   - Combines the dual advantages of accurate content extraction and faster speed in text mode, and more precise span/line region recognition in OCR mode.
@@ -123,6 +142,7 @@ Requires-Dist: albumentations<=1.4.20; extra == "old-linux"
             <li><a href="#online-demo">Online Demo</a></li>
             <li><a href="#quick-cpu-demo">Quick CPU Demo</a></li>
             <li><a href="#using-gpu">Using GPU</a></li>
+            <li><a href="#using-npu">Using NPU</a></li>
             </ul>
         </li>
         <li><a href="#usage">Usage</a>
@@ -171,7 +191,7 @@ https://github.com/user-attachments/assets/4bea02c9-6d54-4cd6-97ed-dff14340982c
 - 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.
+- Supports running in a pure CPU environment, and also supports GPU(CUDA)/NPU(CANN)/MPS acceleration
 - Compatible with Windows, Linux, and Mac platforms.
 
 ## Quick Start
@@ -182,7 +202,10 @@ There are three different ways to experience MinerU:
 
 - [Online Demo (No Installation Required)](#online-demo)
 - [Quick CPU Demo (Windows, Linux, Mac)](#quick-cpu-demo)
-- [Linux/Windows + CUDA](#Using-GPU)
+- Accelerate inference by using CUDA/CANN/MPS
+  - [Linux/Windows + CUDA](#Using-GPU)
+  - [Linux + CANN](#using-npu)
+  - [MacOS + MPS](#using-mps)
 
 > [!WARNING]
 > **Pre-installation Notice—Hardware and Software Environment Support**
@@ -198,20 +221,24 @@ There are three different ways to experience MinerU:
         <td colspan="3" rowspan="2">Operating System</td>
     </tr>
     <tr>
-        <td>Ubuntu 22.04 LTS</td>
+        <td>Linux after 2019</td>
         <td>Windows 10 / 11</td>
         <td>macOS 11+</td>
     </tr>
     <tr>
         <td colspan="3">CPU</td>
-        <td>x86_64(unsupported ARM Linux)</td>
+        <td>x86_64 / arm64</td>
         <td>x86_64(unsupported ARM Windows)</td>
         <td>x86_64 / arm64</td>
     </tr>
     <tr>
-        <td colspan="3">Memory</td>
+        <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(Please make sure to create a Python 3.10 virtual environment using conda)</td>
@@ -228,6 +255,12 @@ There are three different ways to experience MinerU:
         <td>11.8 (manual installation) + cuDNN v8.7.0 (manual installation)</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 Hardware Support List</td>
         <td colspan="2">GPU VRAM 8GB or more</td>
@@ -240,7 +273,7 @@ There are three different ways to experience MinerU:
 ### 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)
+[![OpenDataLab](https://img.shields.io/badge/Demo_on_OpenDataLab-blue?logo=data:image/svg+xml;base64,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&labelColor=white)](https://mineru.org.cn/OpenSourceTools/Extractor?source=github)
 
 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,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&labelColor=white)](https://huggingface.co/spaces/opendatalab/MinerU)
@@ -253,7 +286,7 @@ Test Version (Synced with dev branch updates, testing new features):
 ```bash
 conda create -n MinerU python=3.10
 conda activate MinerU
-pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
+pip install -U "magic-pdf[full]" --extra-index-url https://wheels.myhloli.com
 ```
 
 #### 2. Download model weight files
@@ -278,7 +311,7 @@ You can modify certain configurations in this file to enable or disable features
 {
     // other config
     "layout-config": {
-        "model": "layoutlmv3" // Please change to "doclayout_yolo" when using doclayout_yolo.
+        "model": "doclayout_yolo" // Please change to "layoutlmv3" when using layoutlmv3.
     },
     "formula-config": {
         "mfd_model": "yolo_v8_mfd",
@@ -287,7 +320,7 @@ You can modify certain configurations in this file to enable or disable features
     },
     "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".
+        "enable": true, // The table recognition feature is enabled by default. If you need to disable it, please change the value here to "false".
         "max_time": 400
     }
 }
@@ -309,29 +342,49 @@ If your device supports CUDA and meets the GPU requirements of the mainline envi
 > docker run --rm --gpus=all nvidia/cuda:12.1.0-base-ubuntu22.04 nvidia-smi
 > ```
   ```bash
-  wget https://github.com/opendatalab/MinerU/raw/master/Dockerfile
+  wget https://github.com/opendatalab/MinerU/raw/master/docker/global/Dockerfile -O Dockerfile
   docker build -t mineru:latest .
-  docker run --rm -it --gpus=all mineru:latest /bin/bash
+  docker run --rm -it --gpus=all mineru:latest /bin/bash -c "echo 'source /opt/mineru_venv/bin/activate' >> ~/.bashrc && exec bash"
   magic-pdf --help
   ```
 
+### Using NPU
+
+If your device has NPU acceleration hardware, you can follow the tutorial below to use NPU acceleration:
+
+[Ascend NPU Acceleration](docs/README_Ascend_NPU_Acceleration_zh_CN.md)
+
+### Using MPS
+
+If your device uses Apple silicon chips, you can enable MPS acceleration for certain supported tasks (such as layout detection and formula detection).
+
+You can enable MPS acceleration by setting the `device-mode` parameter to `mps` in the `magic-pdf.json` configuration file.
+
+```json
+{
+    // other config
+    "device-mode": "mps"
+}
+```
+
+> [!TIP]
+> Since the formula recognition task cannot utilize MPS acceleration, you can disable the formula recognition feature in tasks where it is not needed to achieve optimal performance.
+>
+> You can disable the formula recognition feature by setting the `enable` parameter in the `formula-config` section to `false`.
+
 ## Usage
 
 ### Command Line
 
-[Using MinerU via Command Line](https://mineru.readthedocs.io/en/latest/user_guide/quick_start/command_line.html)
+[Using MinerU via Command Line](https://mineru.readthedocs.io/en/latest/user_guide/usage/command_line.html)
 
 > [!TIP]
 > For more information about the output files, please refer to the [Output File Description](docs/output_file_en_us.md).
 
 ### API
 
-[Using MinerU via Python API](https://mineru.readthedocs.io/en/latest/user_guide/quick_start/to_markdown.html)
-
-For detailed implementation, refer to:
+[Using MinerU via Python API](https://mineru.readthedocs.io/en/latest/user_guide/usage/api.html)
 
-- [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