diff --git a/.env.example b/.env.example
new file mode 100644
index 0000000..88fe85b
--- /dev/null
+++ b/.env.example
@@ -0,0 +1,8 @@
+# API配置
+API_KEY=your_api_key_here
+BASE_URL=https://open.bigmodel.cn/api/paas/v4
+MODEL=glm-4v-flash
+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
+
+# 文件处理配置
+FILE_DELETE_DELAY=300  # 5分钟后删除临时文件
\ No newline at end of file
diff --git a/.github/workflows/docker-build.yml b/.github/workflows/docker-build.yml
new file mode 100644
index 0000000..7fd73b1
--- /dev/null
+++ b/.github/workflows/docker-build.yml
@@ -0,0 +1,49 @@
+name: Docker Build and Push
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          build-args: |
+            API_KEY=9dfee4d072cf964f117403933da51242.1s1Tvn56OIGQkvmT
+            BASE_URL=https://open.bigmodel.cn/api/paas/v4
+            MODEL=glm-4v-flash
+            PROMPT=提取图片中全部的文本，不需要任何推理和总结，只需要原文
+            FILE_DELETE_DELAY=300
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..55046f7
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,12 @@
+__pycache__/
+*.py[cod]
+*$py.class
+
+# 环境文件
+.env
+
+# 上传文件目录
+files/
+
+# 虚拟环境
+venv/
\ No newline at end of file
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..e00b5ec
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,36 @@
+# 使用 Python 官方镜像作为基础镜像
+FROM python:3.13-alpine
+
+USER root
+
+# 定义构建参数
+ARG API_KEY
+ARG BASE_URL
+ARG MODEL
+ARG PROMPT
+ARG FILE_DELETE_DELAY
+
+# 设置环境变量
+ENV API_KEY=${API_KEY}
+ENV BASE_URL=${BASE_URL}
+ENV MODEL=${MODEL}
+ENV PROMPT=${PROMPT}
+ENV FILE_DELETE_DELAY=${FILE_DELETE_DELAY}
+ENV PYTHONUNBUFFERED=1
+
+# 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
+
+# 暴露端口（修改为 8000)
+EXPOSE 8000
+
+# 使用 uvicorn 运行 FastAPI 应用，端口改为 8000
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"] 
\ No newline at end of file
diff --git a/README b/README
new file mode 100644
index 0000000..1c15ab9
--- /dev/null
+++ b/README
@@ -0,0 +1,72 @@
+# Image Text Extraction Service
+
+这是一个基于 FastAPI 的图片文本提取服务，支持智谱 AI 的 GLM-4V 模型和阿里云百炼平台的 Qwen-VL-Max 模型进行图片文本识别。
+
+## 环境变量说明
+
+服务支持以下环境变量配置：
+
+| 环境变量 | 说明 | 默认值 |
+|---------|------|--------|
+| API_KEY | AI 平台的 API 密钥 | XXXX |
+| BASE_URL | AI 平台的 API 基础 URL | https://open.bigmodel.cn/api/paas/v4 |
+| MODEL | 使用的模型名称 | glm-4v-flash |
+| DELETE_DELAY | 临时文件删除延迟（秒） | 600 |
+| PROMPT | 文本提取提示词 | 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 |
+
+### 支持的模型配置
+
+#### 智谱 AI
+- MODEL=glm-4v-flash
+- BASE_URL=https://open.bigmodel.cn/api/paas/v4
+
+#### 阿里云百炼
+- MODEL=qwen-vl-max
+- BASE_URL=https://dashscope.aliyuncs.com/api/v1
+
+## Docker 使用说明
+
+### 1. 快速使用（默认使用智谱 AI）
+
+```bash
+docker run -p 8000:8000 pig4cloud/markitdown
+```
+
+### 2. 使用阿里云百炼平台
+
+```bash
+docker run -d \
+  -p 8000:8000 \
+  -e API_KEY=your_aliyun_api_key \
+  -e MODEL=qwen-vl-max \
+  -e BASE_URL=https://dashscope.aliyuncs.com/api/v1 \
+  pig4cloud/markitdown
+```
+
+## API 接口
+
+### 上传图片并提取文本
+
+**Endpoint:** POST /upload/
+
+**请求格式:** multipart/form-data
+
+**参数:**
+- file: 图片文件
+
+**响应示例:**
+```json
+{
+    "new_filename": "1679012345.jpg",
+    "content": "提取的文本内容"
+}
+```
+
+## 注意事项
+
+1. 使用前请确保已获取相应平台的 API 密钥
+2. 智谱 AI 和阿里云百炼平台的接口略有不同，请确保使用正确的配置
+3. 上传的图片文件会在处理后自动删除（默认10分钟）
+4. 服务默认监听 8000 端口
+
+
diff --git a/app/api/endpoints.py b/app/api/endpoints.py
new file mode 100644
index 0000000..f341ed3
--- /dev/null
+++ b/app/api/endpoints.py
@@ -0,0 +1,140 @@
+import os
+import time
+import asyncio
+import fitz  # PyMuPDF
+from fastapi import APIRouter, File, UploadFile, status
+from typing import Dict, Optional, Tuple
+from openai import OpenAI
+from markitdown import MarkItDown
+import tempfile
+
+from app.config import (
+    API_KEY,
+    BASE_URL,
+    MODEL,
+    FILE_DELETE_DELAY,
+    MLM_PROMPT
+)
+from app.utils.file_utils import save_upload_file, delete_files
+
+router = APIRouter()
+
+client = OpenAI(
+    base_url=BASE_URL,
+    api_key=API_KEY
+)
+
+async def process_pdf_page(
+    page: fitz.Page, 
+    markitdown: MarkItDown,
+    mlm_prompt: str
+) -> Optional[str]:
+    """处理单个PDF页面，尝试提取文本或进行OCR识别
+    
+    Args:
+        page: PDF页面对象
+        markitdown: MarkItDown实例
+        mlm_prompt: 文本提取提示
+        
+    Returns:
+        提取的文本内容，如果提取失败返回None
+    """
+    # 首先尝试直接提取文本
+    text = page.get_text().strip()
+    if text:
+        return text
+        
+    # 如果直接提取失败，转换为图片进行OCR
+    try:
+        pix = page.get_pixmap()
+        with tempfile.NamedTemporaryFile(suffix='.png', delete=False) as temp_img:
+            pix.save(temp_img.name)
+            result = markitdown.convert(temp_img.name, mlm_prompt=mlm_prompt)
+            # 清理临时文件
+            os.unlink(temp_img.name)
+            return result.text_content
+    except Exception as e:
+        print(f"页面处理错误: {str(e)}")
+        return None
+
+async def extract_pdf_text(
+    pdf_path: str,
+    markitdown: MarkItDown,
+    mlm_prompt: str
+) -> Tuple[bool, str]:
+    """从PDF文件中提取文本
+    
+    Args:
+        pdf_path: PDF文件路径
+        markitdown: MarkItDown实例
+        mlm_prompt: 文本提取提示
+        
+    Returns:
+        (是否成功, 提取的文本内容)
+    """
+    try:
+        pdf_document = fitz.open(pdf_path)
+        all_text = []
+        
+        for page_num in range(len(pdf_document)):
+            text = await process_pdf_page(
+                pdf_document[page_num],
+                markitdown,
+                mlm_prompt
+            )
+            if text:
+                all_text.append(text)
+                
+        pdf_document.close()
+        
+        if all_text:
+            return True, '\n'.join(all_text)
+        return False, ""
+        
+    except Exception as e:
+        print(f"PDF处理错误: {str(e)}")
+        return False, ""
+
+@router.post("/upload/", 
+    response_model=Dict[str, str],
+    status_code=status.HTTP_200_OK,
+    summary="上传文件",
+    description="上传图片或PDF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": {
+                        "text": "提取的文本内容"
+                    }
+                }
+            }
+        }
+    }
+)
+async def upload_file(
+    file: UploadFile = File(..., description="要上传的文件，支持常见图片格式和PDF文件")
+):
+    timestamp = int(time.time())
+    file_extension = os.path.splitext(file.filename)[1].lower()
+    new_filename = f"{timestamp}{file_extension}"
+    
+    content = await file.read()
+    file_path = await save_upload_file(content, new_filename)
+    
+    markitdown = MarkItDown(mlm_client=client, mlm_model=MODEL)
+    result = markitdown.convert(file_path, mlm_prompt=MLM_PROMPT)
+    
+    # 如果是PDF文件且未提取到文本，则尝试其他方法
+    if file_extension == '.pdf' and not result.text_content:
+        success, text = await extract_pdf_text(file_path, markitdown, MLM_PROMPT)
+        if success:
+            result.text_content = text
+    
+    # 创建异步任务删除临时文件
+    asyncio.create_task(delete_files(file_path, "", FILE_DELETE_DELAY))
+    
+    return {
+        "text": result.text_content or ""
+    }
\ No newline at end of file
diff --git a/app/config.py b/app/config.py
new file mode 100644
index 0000000..99fae74
--- /dev/null
+++ b/app/config.py
@@ -0,0 +1,20 @@
+import os
+from dotenv import load_dotenv
+
+# 加载.env文件
+load_dotenv()
+
+# API配置
+API_KEY = os.getenv('API_KEY')
+BASE_URL = os.getenv('BASE_URL')
+MODEL = os.getenv('MODEL')
+
+# 文件处理配置
+FILE_DELETE_DELAY = int(os.getenv('FILE_DELETE_DELAY', 300))  # 默认5分钟
+MLM_PROMPT = os.getenv('PROMPT')
+
+# 验证必需的环境变量
+required_vars = ['API_KEY', 'BASE_URL', 'MODEL', 'PROMPT']
+missing_vars = [var for var in required_vars if not os.getenv(var)]
+if missing_vars:
+    raise ValueError(f"Missing required environment variables: {', '.join(missing_vars)}")
\ No newline at end of file
diff --git a/app/utils/file_utils.py b/app/utils/file_utils.py
new file mode 100644
index 0000000..75aa1f1
--- /dev/null
+++ b/app/utils/file_utils.py
@@ -0,0 +1,22 @@
+import os
+import asyncio
+import aiofiles
+from typing import Optional
+
+async def save_upload_file(file_content: bytes, filename: str, directory: str = "files") -> str:
+    """保存上传的文件"""
+    if not os.path.exists(directory):
+        os.makedirs(directory)
+    
+    file_path = os.path.join(directory, filename)
+    async with aiofiles.open(file_path, 'wb') as out_file:
+        await out_file.write(file_content)
+    return file_path
+
+async def delete_files(file_path: str, output_path: Optional[str], delay: int):
+    """延迟删除文件"""
+    await asyncio.sleep(delay)
+    if os.path.exists(file_path):
+        os.remove(file_path)
+    if output_path and os.path.exists(output_path):
+        os.remove(output_path) 
\ No newline at end of file
diff --git a/banner.txt b/banner.txt
new file mode 100644
index 0000000..f9a4bdf
--- /dev/null
+++ b/banner.txt
@@ -0,0 +1,8 @@
++----------------------------------------+
+|                                        |
+|         🚀 MarkItDown API Server       |
+|                                        |
+|         ✨ Server is running...        |
+|       🌐http://localhost:8000/docs     |
+|                                        |
++----------------------------------------+ 
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..c3cfdc6
--- /dev/null
+++ b/main.py
@@ -0,0 +1,48 @@
+from pathlib import Path
+from contextlib import asynccontextmanager
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+from fastapi import HTTPException
+
+from app.api.endpoints import router
+
+@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
+
+def create_app() -> FastAPI:
+    app = FastAPI(
+        lifespan=lifespan
+    )
+
+    # Add CORS middleware
+    app.add_middleware(
+        CORSMiddleware,
+        allow_origins=["*"],
+        allow_credentials=True,
+        allow_methods=["*"],
+        allow_headers=["*"],
+    )
+
+    # 注册路由
+    app.include_router(router)
+
+    @app.exception_handler(HTTPException)
+    async def http_exception_handler(request, exc):
+        return JSONResponse(
+            status_code=exc.status_code,
+            content={"message": exc.detail},
+        )
+
+    return app
+
+app = create_app()
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..bf0549c
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,9 @@
+fastapi
+aiofiles
+markitdown
+uvicorn
+openai
+socksio
+PyMuPDF
+python-multipart
+python-dotenv==1.0.1