Metadata-Version: 2.4
Name: ai-document-intelligence
Version: 0.1.0
Summary: A production-ready Python SDK for intelligent PDF parsing for LLM applications.
Author: Vishal Choudhary
License: MIT
License-File: LICENSE
Requires-Python: >=3.12
Requires-Dist: pydantic>=2.11.0
Requires-Dist: pymupdf>=1.26.0
Description-Content-Type: text/markdown

# AI Document Intelligence

Python SDK for intelligent PDF parsing for AI and LLM applications.

## Installation

```bash
pip install ai-document-intelligence
```

## Usage

```python
from ai_document_intelligence import DocumentParser

parser = DocumentParser()

document = parser.parse("annual_report.pdf")

print(document.metadata.page_count)
print(document.pages[0].text)
```

## Current Features

- PDF Parsing
- PyMuPDF Backend
- Metadata Extraction
- Page-wise Text Extraction
- Raw Text Extraction

## Roadmap

- Docling
- OCR
- Tables
- Layout Detection
- Smart Chunking