first commit

Author: lltx

.github/workflows/docker-build.yml

@@ -0,0 +1,33 @@
+name: Docker Build and Push
+
+on:
+  push:
+    branches: [ "main" ]  # 当推送到main分支时触发
+  pull_request:
+    branches: [ "main" ]  # 当创建针对main分支的PR时触发
+  # 允许手动触发工作流
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: pig4cloud
+          password: a123.+-
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: |
+            ${{ secrets.DOCKERHUB_USERNAME }}/office2md:latest

.gitignore

@@ -0,0 +1 @@
+envs/

Dockerfile

@@ -0,0 +1,24 @@
+# 使用 Python 官方镜像作为基础镜像
+FROM python:3.13-alpine
+
+USER root
+
+# Runtime dependency
+RUN apk add --no-cache ffmpeg
+
+# 设置工作目录
+WORKDIR /app
+
+# 复制项目文件到容器中
+COPY . .
+
+RUN pip3 install -r requirements.txt
+
+# 设置环境变量
+ENV PYTHONUNBUFFERED=1
+
+# 暴露端口（FastAPI 默认使用 8000 端口）
+EXPOSE 8000
+
+# 使用 uvicorn 运行 FastAPI 应用
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"] 

banner.txt

@@ -0,0 +1,8 @@
++----------------------------------------+
+|                                        |
+|         🚀 MarkItDown API Server       |
+|                                        |
+|         ✨ Server is running...        |
+|     🌐 Visit http://localhost:8000/docs |
+|                                        |
++----------------------------------------+ 

files/1734436182.png

@@ -0,0 +1,101 @@
+import os
+import time
+import asyncio
+from fastapi import FastAPI, File, UploadFile, HTTPException, status
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import FileResponse
+import aiofiles
+from markitdown import MarkItDown
+from starlette.responses import JSONResponse
+from urllib.parse import unquote
+from openai import OpenAI
+from contextlib import asynccontextmanager
+from pathlib import Path
+from typing import Dict
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # 启动时执行
+    banner_path = Path(__file__).parent / 'banner.txt'
+    try:
+        with open(banner_path, 'r', encoding='utf-8') as f:
+            banner = f.read()
+        print(banner)
+    except FileNotFoundError:
+        print("Banner file not found, starting server without banner...")
+    yield
+app = FastAPI(lifespan=lifespan)
+
+client = OpenAI(
+    base_url="https://open.bigmodel.cn/api/paas/v4",
+    api_key="9dfee4d072cf964f117403933da51242.1s1Tvn56OIGQkvmT"
+)
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all methods
+    allow_headers=["*"],  # Allows all headers
+)
+
+async def delete_files(file_path: str, output_path: str, delay: int):
+    await asyncio.sleep(delay)
+    if os.path.exists(file_path):
+        os.remove(file_path)
+    if os.path.exists(output_path):
+        os.remove(output_path)
+
+@app.post("/upload/", 
+    response_model=Dict[str, str],
+    status_code=status.HTTP_200_OK,
+    summary="上传图片文件",
+    description="上传图片文件并提取其中的文本内容",
+    responses={
+        200: {
+            "description": "成功提取文本",
+            "content": {
+                "application/json": {
+                    "example": {
+                        "new_filename": "1679012345.jpg",
+                        "content": "提取的文本内容"
+                    }
+                }
+            }
+        }
+    }
+)
+async def upload_file(
+    file: UploadFile = File(..., description="要上传的图片文件，支持常见图片格式")
+):
+    if not os.path.exists('tmp'):
+        os.makedirs('tmp')
+
+    original_filename = os.path.splitext(file.filename)[0]
+    timestamp = int(time.time())
+    file_extension = os.path.splitext(file.filename)[1]
+    new_filename = f"{timestamp}{file_extension}"
+    file_path = f"files/{new_filename}"
+
+    async with aiofiles.open(file_path, 'wb') as out_file:
+        content = await file.read()
+        await out_file.write(content)
+
+    markitdown = MarkItDown(mlm_client=client, mlm_model="glm-4v-flash")
+    result = markitdown.convert(file_path, mlm_prompt="提取图片中全部的文本，不需要任何推理和总结，只需要原文")
+
+    # Schedule file deletion after 10 minutes (600 seconds)
+    asyncio.create_task(delete_files(file_path, "", 600))
+
+    return {
+        "new_filename": new_filename,
+        "content": result.text_content
+    }
+
+@app.exception_handler(HTTPException)
+async def http_exception_handler(request, exc):
+    return JSONResponse(
+        status_code=exc.status_code,
+        content={"message": exc.detail},
+    )

files/1734436193.png

@@ -0,0 +1,7 @@
+fastapi
+aiofiles
+markitdown
+uvicorn
+openai
+socksio
+python-multipart