Markitdown

# MarkItDown Example Usage

This document provides practical examples of using MarkItDown in various scenarios.

## Basic Examples

### 1. Simple File Conversion

```python
from markitdown import MarkItDown

md = MarkItDown()

# Convert a PDF
result = md.convert("research_paper.pdf")
print(result.text_content)

# Convert a Word document
result = md.convert("manuscript.docx")
print(result.text_content)

# Convert a PowerPoint
result = md.convert("presentation.pptx")
print(result.text_content)
```

### 2. Save to File

```python
from markitdown import MarkItDown

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

with open("output.md", "w", encoding="utf-8") as f:
    f.write(result.text_content)
```

### 3. Convert from Stream

```python
from markitdown import MarkItDown

md = MarkItDown()

with open("document.pdf", "rb") as f:
    result = md.convert_stream(f, file_extension=".pdf")
    print(result.text_content)
```

## Scientific Workflows

### Convert Research Papers

```python
from markitdown import MarkItDown
from pathlib import Path

md = MarkItDown()

# Convert all papers in a directory
papers_dir = Path("research_papers/")
output_dir = Path("markdown_papers/")
output_dir.mkdir(exist_ok=True)

for paper in papers_dir.glob("*.pdf"):
    result = md.convert(str(paper))
    
    # Save with original filename
    output_file = output_dir / f"{paper.stem}.md"
    output_file.write_text(result.text_content)
    
    print(f"Converted: {paper.name}")
```

### Extract Tables from Excel

```python
from markitdown import MarkItDown

md = MarkItDown()

# Convert Excel to Markdown tables
result = md.convert("experimental_data.xlsx")

# The result contains Markdown-formatted tables
print(result.text_content)

# Save for further processing
with open("data_tables.md", "w") as f:
    f.write(result.text_content)
```

### Process Presentation Slides

```python
from markitdown import MarkItDown
from openai import OpenAI

# With AI descriptions for images
client = OpenAI()
md = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",
    llm_prompt="Describe this scientific slide, focusing on data and key findings"
)

result = md.convert("conference_talk.pptx")

# Save with metadata
output = f"""# Conference Talk

{result.text_content}
"""

with open("talk_notes.md", "w") as f:
    f.write(output)
```

## AI-Enhanced Conversions

### Detailed Image Descriptions

```python
from markitdown import MarkItDown
from openai import OpenAI

# Initialize OpenRouter client
client = OpenAI(
    api_key="your-openrouter-api-key",
    base_url="https://openrouter.ai/api/v1"
)

# Scientific diagram analysis
scientific_prompt = """
Analyze this scientific figure. Describe:
- Type of visualization (graph, microscopy, diagram, etc.)
- Key data points and trends
- Axes, labels, and legends
- Scientific significance
Be technical and precise.
"""

md = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",  # recommended for scientific vision
    llm_prompt=scientific_prompt
)

# Convert paper with figures
result = md.convert("paper_with_figures.pdf")
print(result.text_content)
```

### Different Prompts for Different Files

```python
from markitdown import MarkItDown
from openai import OpenAI

# Initialize OpenRouter client
client = OpenAI(
    api_key="your-openrouter-api-key",
    base_url="https://openrouter.ai/api/v1"
)

# Scientific papers - use Claude for technical analysis
scientific_md = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",
    llm_prompt="Describe scientific figures with technical precision"
)

# Presentations - use GPT-4o for visual understanding
presentation_md = MarkItDown(
    llm_client=client,
    llm_model="anthropic/claude-sonnet-4.5",
    llm_prompt="Summarize slide content and key visual elements"
)

# Use appropriate instance for each file
paper_result = scientific_md.convert("research.pdf")
slides_result = presentation_md.convert("talk.pptx")
`