Merge pull request #838 from opendatalab/release-0.9.0

Release 0.9.0

projects/web/src/utils/locale.ts

+export enum ELocal {
+  "zh-CN" = "zh-CN",
+  "en-US" = "en-US",
+}
+export const locale: { [key: string]: string } = {
+  [ELocal["zh-CN"]]: "中文",
+  [ELocal["en-US"]]: "En",
+};
+export const localeName: { [key: string]: string } = {
+  [ELocal["zh-CN"]]: "nameZh",
+  [ELocal["en-US"]]: "name",
+};
+
+export const getLocale = () => {
+  return localStorage.getItem("umi_locale") || ELocal["zh-CN"];
+};

projects/web/src/utils/windowOpen.ts

+export const windowOpen = (
+  url: string,
+  type?: "_blank" | "_parent" | "_self" | "_top"
+) => {
+  const a = document.createElement("a");
+  a.setAttribute("href", url);
+  a.setAttribute("target", type || "_blank");
+  a.rel = "noreferrer";
+  document.body.appendChild(a);
+  if (a.click) {
+    a?.click();
+  } else {
+    try {
+      let evt = new Event("click", {
+        bubbles: false,
+        cancelable: true,
+      });
+      a.dispatchEvent(evt);
+    } catch (error) {
+      window.open(url, type || "_blank");
+    }
+  }
+  document.body.removeChild(a);
+};

projects/web/src/vite-env.d.ts

+/// <reference types="vite/client" />

projects/web/tailwind.config.js

+module.exports = {
+  content: [
+    "./src/**/*.{js,jsx,ts,tsx}",
+  ],
+  plugins: [
+    function ({ addUtilities }) {
+      const newUtilities = {
+        '.scrollbar-thin': {
+          scrollbarWidth: '2px',
+          // scrollbarColor: 'rgba(13, 83, 222, 1)',
+          '&::-webkit-scrollbar': {
+            width: '6px',
+            height: '6px'
+          },
+          '&::-webkit-scrollbar-track': {
+            backgroundColor: 'transparent'
+          },
+          '&::-webkit-scrollbar-thumb': {
+            // backgroundColor: 'rgba(13, 83, 222, 0.01)',
+            borderRadius: '20px',
+            border: '3px solid transparent'
+          },
+          '&:hover::-webkit-scrollbar-thumb': {
+            width: '6px',
+            border: '3px solid rgb(229 231 235)',
+            backgroundColor: 'rgb(229 231 235)'
+          }
+        }
+        // 你可以添加更多自定义的滚动条样式
+      };
+      addUtilities(newUtilities, ['responsive', 'hover']);
+    },
+  ],
+  // ...other configurations
+}
\ No newline at end of file

projects/web/tsconfig.app.json

+{
+  "compilerOptions": {
+    "target": "ES2020",
+    "useDefineForClassFields": true,
+    "lib": ["ES2020", "DOM", "DOM.Iterable"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+
+    /* Bundler mode */
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "isolatedModules": true,
+    "moduleDetection": "force",
+    "noEmit": true,
+    "jsx": "react-jsx",
+
+    /* Linting */
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true,
+    "paths": {
+      "@/*": ["./src/*"]
+    }
+  },
+  "include": ["src"]
+}

projects/web/tsconfig.json

+{
+  "files": [],
+  "compilerOptions": {
+    // ... other options ...
+    "types": ["node"]
+  },
+  "references": [
+    { "path": "./tsconfig.app.json" },
+    { "path": "./tsconfig.node.json" }
+  ]
+}

projects/web/tsconfig.node.json

+{
+  "compilerOptions": {
+    "target": "ES2022",
+    "lib": ["ES2023"],
+    "module": "ESNext",
+    "skipLibCheck": true,
+
+    /* Bundler mode */
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "isolatedModules": true,
+    "moduleDetection": "force",
+    "noEmit": true,
+
+    /* Linting */
+    "strict": true,
+    "noUnusedLocals": true,
+    "noUnusedParameters": true,
+    "noFallthroughCasesInSwitch": true
+  },
+  "include": ["vite.config.ts"]
+}

projects/web/vite.config.ts

+import { defineConfig } from "vite";
+import react from "@vitejs/plugin-react";
+import path from "path";
+
+// https://vitejs.dev/config/
+export default defineConfig({
+  plugins: [react()],
+  server: {
+    proxy: {
+      "/api": {
+        target: "http://localhost:5559",
+        changeOrigin: true,
+      },
+    },
+  },
+  css: {
+    modules: {
+      localsConvention: "camelCaseOnly", // transfer kebab-case to camelCase
+      scopeBehaviour: "local",
+      generateScopedName: "[name]__[local]___[hash:base64:5]",
+    },
+  },
+  publicDir: "public",
+  resolve: {
+    alias: {
+      "@": path.resolve(__dirname, "./src"),
+    },
+  },
+});

projects/web_api/Dockerfile

+# Use the official Ubuntu base image
+FROM ubuntu:latest
+
+# ENV http_proxy http://127.0.0.1:7890
+# ENV https_proxy http://127.0.0.1:7890
+
+# Set environment variables to non-interactive to avoid prompts during installation
+ENV DEBIAN_FRONTEND=noninteractive
+ENV LANG C.UTF-8
+
+# ADD sources.list /etc/apt
+# RUN apt-get clean
+
+
+
+# Update the package list and install necessary packages
+RUN apt-get -q update \
+    && apt-get -q install -y --no-install-recommends \
+        apt-utils \
+        bats \
+        build-essential
+RUN apt-get update && apt-get install -y vim net-tools procps lsof curl wget iputils-ping telnet lrzsz git
+
+RUN apt-get update && \
+    apt-get install -y \
+        software-properties-common && \
+    add-apt-repository ppa:deadsnakes/ppa && \
+    apt-get update && \
+    apt-get install -y \
+        python3.10 \
+        python3.10-venv \
+        python3.10-distutils \
+        python3-pip \
+        wget \
+        git \
+        libgl1 \
+        libglib2.0-0 \
+        && rm -rf /var/lib/apt/lists/*
+        
+# RUN unset http_proxy && unset https_proxy
+
+# Set Python 3.10 as the default python3
+RUN update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.10 1
+
+# Create a virtual environment for MinerU
+RUN python3 -m venv /opt/mineru_venv
+RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple
+# Activate the virtual environment and install necessary Python packages
+RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
+    pip install --upgrade pip && \
+    pip install magic-pdf[full] --extra-index-url https://myhloli.github.io/wheels/ --no-cache-dir"
+
+
+RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
+    pip install fastapi uvicorn python-multipart --no-cache-dir"
+
+RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
+    pip uninstall  paddlepaddle -y"
+
+RUN /bin/bash -c "source /opt/mineru_venv/bin/activate && \
+    python -m pip install paddlepaddle-gpu==3.0.0b1 -i https://www.paddlepaddle.org.cn/packages/stable/cu118/ --no-cache-dir"
+
+# Copy the configuration file template and set up the model directory
+COPY magic-pdf.template.json /root/magic-pdf.json
+ADD models /opt/models
+ADD .paddleocr /root/.paddleocr 
+ADD app.py /root/app.py
+
+WORKDIR /root
+
+# Set the models directory in the configuration file (adjust the path as needed)
+RUN sed -i 's|/tmp/models|/opt/models|g' /root/magic-pdf.json
+
+# Create the models directory
+# RUN mkdir -p /opt/models
+
+# Set the entry point to activate the virtual environment and run the command line tool
+# ENTRYPOINT ["/bin/bash", "-c", "source /opt/mineru_venv/bin/activate && exec \"$@\" && python3 app.py", "--"]
+
+
+# Expose the port that FastAPI will run on
+EXPOSE 8000
+
+# Command to run FastAPI using Uvicorn, pointing to app.py and binding to 0.0.0.0:8000
+CMD ["/bin/bash", "-c", "source /opt/mineru_venv/bin/activate && uvicorn app:app --host 0.0.0.0 --port 8000"]
\ No newline at end of file

projects/web_api/README.md

+基于MinerU的PDF解析API
+
+    - MinerU的GPU镜像构建
+    - 基于FastAPI的PDF解析接口
+
+支持一键启动，已经打包到镜像中，自带模型权重，支持GPU推理加速，GPU速度相比CPU每页解析要快几十倍不等
+
+
+##  启动命令：
+
+
+```docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.1-models```
+
+![](https://i-blog.csdnimg.cn/direct/bcff4f524ea5400db14421ba7cec4989.png)
+
+具体截图请见博客：https://blog.csdn.net/yanqianglifei/article/details/141979684
+
+
+##   启动日志：
+
+![](https://i-blog.csdnimg.cn/direct/4eb5657567e4415eba912179dca5c8aa.png)
+
+##  输入参数：
+
+访问地址：
+
+    http://localhost:8888/docs
+
+    http://127.0.01:8888/docs
+
+![](https://i-blog.csdnimg.cn/direct/8b3a2bc5908042268e8cc69756e331a2.png)
+
+##  解析效果：
+
+![](https://i-blog.csdnimg.cn/direct/a54dcae834ae48d498fb595aca4212c3.png)
+
+
+
+##   镜像地址：
+
+> 阿里云地址：docker pull registry.cn-beijing.aliyuncs.com/quincyqiang/mineru:0.1-models
+
+> dockerhub地址：docker pull quincyqiang/mineru:0.1-models
+

projects/web_api/app.py

+import copy
+import json
+import os
+from tempfile import NamedTemporaryFile
+
+import magic_pdf.model as model_config
+import uvicorn
+from fastapi import FastAPI, File, UploadFile, Form
+from fastapi.responses import JSONResponse
+from loguru import logger
+from magic_pdf.pipe.OCRPipe import OCRPipe
+from magic_pdf.pipe.TXTPipe import TXTPipe
+from magic_pdf.pipe.UNIPipe import UNIPipe
+from magic_pdf.rw.DiskReaderWriter import DiskReaderWriter
+
+model_config.__use_inside_model__ = True
+
+app = FastAPI()
+
+def json_md_dump(
+        pipe,
+        md_writer,
+        pdf_name,
+        content_list,
+        md_content,
+):
+    # Write model results to model.json
+    orig_model_list = copy.deepcopy(pipe.model_list)
+    md_writer.write(
+        content=json.dumps(orig_model_list, ensure_ascii=False, indent=4),
+        path=f"{pdf_name}_model.json"
+    )
+
+    # Write intermediate results to middle.json
+    md_writer.write(
+        content=json.dumps(pipe.pdf_mid_data, ensure_ascii=False, indent=4),
+        path=f"{pdf_name}_middle.json"
+    )
+
+    # Write text content results to content_list.json
+    md_writer.write(
+        content=json.dumps(content_list, ensure_ascii=False, indent=4),
+        path=f"{pdf_name}_content_list.json"
+    )
+
+    # Write results to .md file
+    md_writer.write(
+        content=md_content,
+        path=f"{pdf_name}.md"
+    )
+
+@app.post("/pdf_parse", tags=["projects"], summary="Parse PDF file")
+async def pdf_parse_main(
+        pdf_file: UploadFile = File(...),
+        parse_method: str = 'auto',
+        model_json_path: str = None,
+        is_json_md_dump: bool = True,
+        output_dir: str = "output"
+):
+    """
+    Execute the process of converting PDF to JSON and MD, outputting MD and JSON files to the specified directory
+    :param pdf_file: The PDF file to be parsed
+    :param parse_method: Parsing method, can be auto, ocr, or txt. Default is auto. If results are not satisfactory, try ocr
+    :param model_json_path: Path to existing model data file. If empty, use built-in model. PDF and model_json must correspond
+    :param is_json_md_dump: Whether to write parsed data to .json and .md files. Default is True. Different stages of data will be written to different .json files (3 in total), md content will be saved to .md file
+    :param output_dir: Output directory for results. A folder named after the PDF file will be created to store all results
+    """
+    try:
+        # Create a temporary file to store the uploaded PDF
+        with NamedTemporaryFile(delete=False, suffix=".pdf") as temp_pdf:
+            temp_pdf.write(await pdf_file.read())
+            temp_pdf_path = temp_pdf.name
+
+        pdf_name = os.path.basename(pdf_file.filename).split(".")[0]
+
+        if output_dir:
+            output_path = os.path.join(output_dir, pdf_name)
+        else:
+            output_path = os.path.join(os.path.dirname(temp_pdf_path), pdf_name)
+
+        output_image_path = os.path.join(output_path, 'images')
+
+        # Get parent path of images for relative path in .md and content_list.json
+        image_path_parent = os.path.basename(output_image_path)
+
+        pdf_bytes = open(temp_pdf_path, "rb").read()  # Read binary data of PDF file
+
+        if model_json_path:
+            # Read original JSON data of PDF file parsed by model, list type
+            model_json = json.loads(open(model_json_path, "r", encoding="utf-8").read())
+        else:
+            model_json = []
+
+        # Execute parsing steps
+        image_writer, md_writer = DiskReaderWriter(output_image_path), DiskReaderWriter(output_path)
+
+        # Choose parsing method
+        if parse_method == "auto":
+            jso_useful_key = {"_pdf_type": "", "model_list": model_json}
+            pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
+        elif parse_method == "txt":
+            pipe = TXTPipe(pdf_bytes, model_json, image_writer)
+        elif parse_method == "ocr":
+            pipe = OCRPipe(pdf_bytes, model_json, image_writer)
+        else:
+            logger.error("Unknown parse method, only auto, ocr, txt allowed")
+            return JSONResponse(content={"error": "Invalid parse method"}, status_code=400)
+
+        # Execute classification
+        pipe.pipe_classify()
+
+        # If no model data is provided, use built-in model for parsing
+        if not model_json:
+            if model_config.__use_inside_model__:
+                pipe.pipe_analyze()  # Parse
+            else:
+                logger.error("Need model list input")
+                return JSONResponse(content={"error": "Model list input required"}, status_code=400)
+
+        # Execute parsing
+        pipe.pipe_parse()
+
+        # Save results in text and md format
+        content_list = pipe.pipe_mk_uni_format(image_path_parent, drop_mode="none")
+        md_content = pipe.pipe_mk_markdown(image_path_parent, drop_mode="none")
+
+        if is_json_md_dump:
+            json_md_dump(pipe, md_writer, pdf_name, content_list, md_content)
+        data = {"layout": copy.deepcopy(pipe.model_list), "info": pipe.pdf_mid_data, "content_list": content_list,'md_content':md_content}
+        return JSONResponse(data, status_code=200)
+
+    except Exception as e:
+        logger.exception(e)
+        return JSONResponse(content={"error": str(e)}, status_code=500)
+    finally:
+        # Clean up the temporary file
+        if 'temp_pdf_path' in locals():
+            os.unlink(temp_pdf_path)
+
+# if __name__ == '__main__':
+#     uvicorn.run(app, host="0.0.0.0", port=8888)
\ No newline at end of file

projects/web_api/magic-pdf.json

+{
+    "bucket_info":{
+        "bucket-name-1":["ak", "sk", "endpoint"],
+        "bucket-name-2":["ak", "sk", "endpoint"]
+    },
+    "models-dir":"/opt/models",
+    "device-mode":"cuda",
+    "table-config": {
+        "model": "TableMaster",
+        "is_table_recog_enable": false,
+        "max_time": 400
+    }
+}

projects/web_api/magic-pdf.template.json

+{
+    "bucket_info":{
+        "bucket-name-1":["ak", "sk", "endpoint"],
+        "bucket-name-2":["ak", "sk", "endpoint"]
+    },
+    "models-dir":"/tmp/models",
+    "device-mode":"cuda",
+    "table-config": {
+        "model": "TableMaster",
+        "is_table_recog_enable": false,
+        "max_time": 400
+    }
+}
\ No newline at end of file

projects/web_api/sources.list

+deb http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
+deb-src http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
+deb http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
+deb-src http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
+deb http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
+deb-src http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
+deb http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
+deb-src http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
+deb http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse
+deb-src http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse
\ No newline at end of file

projects/web_api/start_mineru.sh

+docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.1-models /bin/bash
+
+docker run -itd --name=mineru_server --gpus=all -p 8888:8000 quincyqiang/mineru:0.3-models
+
+docker login --username=1185918903@qq.com registry.cn-beijing.aliyuncs.com
+docker tag quincyqiang/mineru:0.3-models registry.cn-beijing.aliyuncs.com/quincyqiang/gomate:0.3-models
+docker push registry.cn-beijing.aliyuncs.com/quincyqiang/gomate:0.3-models
\ No newline at end of file

projects/web_demo/README.md

+# MinerU Local web_demo
+## Feature Overview
+<p align="center">
+  <img src="images/web_demo_1.png" width="600px" style="vertical-align:middle;">
+</p>
+
+- Supports uploading PDFs and calling MinerU for processing
+
+- Supports online editing of the Markdown results parsed by MinerU
+
+- Supports viewing of historical tasks
+
+## Installation and Deployment
+
+0. MinerU Installation and Deployment
+
+
+```
+# The service depends on mineru, please ensure mineru is installed first
+```
+
+1. Package the front-end interface
+
+```bash
+# First, navigate to the front-end directory
+cd projects/web
+
+# Modify the configuration
+# Change the IP in the target field of the file vite.config.ts to your own computer's IP
+
+# Build the front-end project
+npm install -g yarn
+yarn install
+yarn build
+```
+
+2. Install service dependencies
+
+```bash
+# First, navigate to the back-end directory
+cd projects/web_demo
+# Install dependencies
+pip3 install -r requirements.txt  -i https://mirrors.aliyun.com/pypi/simple
+```
+
+3. Start the service
+
+```bash
+# Navigate to the program directory
+cd projects/web_demo/web_demo
+# Start the service
+python3 app.py or python app.py
+# Access the interface by visiting the started address in the browser
+```
+
+ps：API documentation
+
+```
+Open the mineru-web API mineru-web接口文档.html in the browser
+```

projects/web_demo/README_zh-CN.md

+# MinerU本地web_demo
+## 功能简介
+<p align="center">
+  <img src="images/web_demo_1.png" width="600px" style="vertical-align:middle;">
+</p>
+
+- 支持上传pdf，并调用MinerU进行处理
+
+- 支持对MinerU解析的Markdown结果进行在线修改
+
+- 支持查看历史任务
+
+## 安装部署
+
+0. MinerU安装部署
+
+```
+# 服务依赖MinerU，请先确保MinerU已安装
+```
+
+1. 打包前端界面
+
+```bash
+# 先进入前端目录
+cd projects/web
+
+# 修改配置
+# 将文件vite.config.ts中的target中的IP更改为自己电脑IP
+
+# 打包前端项目
+npm install -g yarn
+yarn install
+yarn build
+```
+
+2. 安装服务依赖
+
+```bash
+# 先进入后端目录
+cd projects/web_demo
+# 安装依赖
+pip3 install -r requirements.txt  -i https://mirrors.aliyun.com/pypi/simple
+```
+
+3. 启动服务
+
+```bash
+# 进入程序目录
+cd projects/web_demo/web_demo
+# 启动服务
+python3 app.py 或者 python app.py
+# 在浏览器访问启动的地址即可访问界面
+```
+
+ps：接口文档
+
+```
+在浏览器打开 mineru-web接口文档.html
+```