# 安装所有格式支持
pip install 'markitdown[all]'

# 只安装PDF支持
pip install 'markitdown[pdf]'

# 只安装Office三件套
pip install 'markitdown[pptx,docx,xlsx]'

# 安装PDF+DOCX+PPTX
pip install 'markitdown[pdf,docx,pptx]'

# 标准Python
python -m venv .venv
source .venv/bin/activate  # Linux/macOS
# 或
.venv\Scripts\activate     # Windows

# 使用uv（更推荐）
uv venv --python=3.12 .venv
source .venv/bin/activate

# 输出到stdout
markitdown path-to-file.pdf > document.md

# 指定输出文件
markitdown path-to-file.pdf -o document.md

# 管道输入
cat path-to-file.pdf | markitdown

docker build -t markitdown:latest .
docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md

from markitdown import MarkItDown

md = MarkItDown(enable_plugins=False)
result = md.convert("test.xlsx")
print(result.text_content)

from markitdown import MarkItDown

md = MarkItDown(enable_plugins=True)
result = md.convert("document_with_images.pdf")
print(result.text_content)

from markitdown import MarkItDown

md = MarkItDown(docintel_endpoint="<your_endpoint>")
result = md.convert("test.pdf")
print(result.text_content)

markitdown --list-plugins

markitdown --use-plugins path-to-file.pdf

# 查看MCP包
markitdown --help  # 或查看 packages/markitdown-mcp

pip install markitdown-ocr
pip install openai  # 或任何OpenAI兼容客户端

from markitdown import MarkItDown
from openai import OpenAI

md = MarkItDown(
    enable_plugins=True,
    llm_client=OpenAI(),      # LLM客户端
    llm_model="gpt-4o"        # 使用的模型
)
result = md.convert("document_with_images.pdf")
print(result.text_content)

# CLI使用
markitdown path-to-file.pdf -o document.md -d -e "<document_intelligence_endpoint>"

from markitdown import MarkItDown

md = MarkItDown(docintel_endpoint="<your_endpoint>")
result = md.convert("test.pdf")
print(result.text_content)

from markitdown import MarkItDown
from openai import OpenAI

client = OpenAI()

md = MarkItDown(
    llm_client=client,
    llm_model="gpt-4o",
    llm_prompt="用中文描述这张图片的内容"
)
result = md.convert("example.jpg")
print(result.text_content)

from markitdown import MarkItDown

def extract_document(file_path: str) -> str:
    """RAG管道的文档提取步骤"""
    md = MarkItDown(enable_plugins=True)
    result = md.convert(file_path)
    return result.text_content

# 使用示例
content = extract_document("quarterly_report.pdf")
# 后续可进行分块、嵌入、存储

from markitdown import MarkItDown
from pathlib import Path

def batch_convert(directory: str, output_dir: str):
    """批量转换目录下所有支持的文件"""
    md = MarkItDown()
    input_path = Path(directory)
    output_path = Path(output_dir)
    output_path.mkdir(parents=True, exist_ok=True)

    for file in input_path.rglob("*"):
        if file.suffix.lower() in ['.pdf', '.docx', '.pptx', '.xlsx']:
            try:
                result = md.convert(str(file))
                output_file = output_path / f"{file.stem}.md"
                output_file.write_text(result.text_content)
                print(f"✓ {file.name} → {output_file.name}")
            except Exception as e:
                print(f"✗ {file.name}: {e}")

batch_convert("./documents", "./markdown")

from markitdown import MarkItDown

md = MarkItDown()

# convert_stream需要二进制文件对象
with open("document.pdf", "rb") as f:
    result = md.convert_stream(f)
    print(result.text_content)

from markitdown import MarkItDown
from openai import OpenAI

client = OpenAI()

md = MarkItDown(
    llm_client=client,
    llm_model="gpt-4o",
    llm_prompt="请用简洁的简体中文描述这张图片，用于后续检索。\
                重点关注：文字内容、数据图表、产品名称。"
)
result = md.convert("product_image.jpg")
print(result.text_content)

from markitdown import MarkItDown

md = MarkItDown(enable_plugins=True)
result = md.convert("document.pdf")

# 查看完整结果对象
print(f"File: {result.file_name}")
print(f"Content Type: {result.content_type}")
print(f"Text Content: {result.text_content[:500]}...")

# 全量安装（推荐）
pip install 'markitdown[all]'

# 常用组合
pip install 'markitdown[pdf,docx,pptx]'

# PDF + 图片OCR
pip install 'markitdown[pdf]' markitdown-ocr openai

# YouTube视频转录
pip install 'markitdown[youtube-transcription]'