llm-data-converter 0.2.0

Convert any document, text, or URL into LLM-ready data format

LLM Data Converter

Convert any document, text, or URL into LLM-ready data format.

Installation

pip install llm-data-converter

System Dependencies for OCR

For OCR functionality to work properly, you may need to install additional system dependencies:

Ubuntu/Debian:

sudo apt update
sudo apt install -y libgl1-mesa-glx libglib2.0-0

macOS:

# Usually not needed, but if you encounter OpenGL issues:
brew install mesa

Windows:

# Usually not needed, but if you encounter OpenGL issues:
# Install the latest graphics drivers from your GPU manufacturer

Optional Dependencies

For better OCR error detection and debugging:

pip install llm-data-converter[opencv]

Quick Start

from llm_converter import FileConverter
from litellm import completion

# Basic conversion
converter = FileConverter()
result = converter.convert("document.pdf").to_markdown()

# Pass the result to LLM
response = completion(
    model="openai/gpt-4o",
    messages=[{"content": f"Extract info from this document: \n{result}", "role": "user"}]
)

Features

• Multiple Input Formats: PDF, DOCX, TXT, HTML, URLs, Excel files, and more
• Multiple Output Formats: Markdown, HTML, JSON, Plain Text
• LLM Integration: Seamless integration with LiteLLM and other LLM libraries
• Local Processing: Process documents locally without external dependencies
• Layout Preservation: Maintain document structure and formatting

Usage Examples

Convert PDF to Markdown

from llm_converter import FileConverter

converter = FileConverter()
result = converter.convert("document.pdf").to_markdown()
print(result)

Convert URL to HTML

from llm_converter import FileConverter

converter = FileConverter()
result = converter.convert("https://example.com").to_html()
print(result)

Convert Excel to JSON

from llm_converter import FileConverter

converter = FileConverter()
result = converter.convert("data.xlsx").to_json()
print(result)

Chain with LLM

from llm_converter import FileConverter
from litellm import completion

converter = FileConverter()
document_content = converter.convert("report.pdf").to_markdown()

# Use with any LLM
response = completion(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant that analyzes documents."},
        {"role": "user", "content": f"Summarize this document:\n\n{document_content}"}
    ]
)

print(response.choices[0].message.content)

Supported Formats

Input Formats

• Documents: PDF, DOCX, TXT
• Web: URLs, HTML files
• Data: Excel (XLSX, XLS), CSV
• Images: PNG, JPG, JPEG (with OCR capabilities)

Output Formats

• Markdown: Clean, structured markdown
• HTML: Formatted HTML with styling
• JSON: Structured JSON data
• Plain Text: Simple text extraction

Advanced Usage

Custom Configuration

from llm_converter import FileConverter

converter = FileConverter(
    preserve_layout=True,
    include_images=True,
    ocr_enabled=True
)

result = converter.convert("document.pdf").to_markdown()

Batch Processing

from llm_converter import FileConverter

converter = FileConverter()
files = ["doc1.pdf", "doc2.docx", "doc3.xlsx"]

results = []
for file in files:
    result = converter.convert(file).to_markdown()
    results.append(result)

API Reference

FileConverter

Main class for converting documents to LLM-ready formats.

Methods

• convert(file_path: str) -> ConversionResult: Convert a file to internal format
• convert_url(url: str) -> ConversionResult: Convert a URL to internal format
• convert_text(text: str) -> ConversionResult: Convert plain text to internal format

ConversionResult

Result object with methods to export to different formats.

Methods

• to_markdown() -> str: Export as markdown
• to_html() -> str: Export as HTML
• to_json() -> dict: Export as JSON
• to_text() -> str: Export as plain text

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

License

MIT License - see LICENSE file for details.