feat: Add PDF Table Extract Tool

[sachinspanicker]

PDF Table Extract Tool

Description

Add new PDFTableExtractTool for extracting tables from PDF documents and converting them to markdown format.

Features

• Extract tables from PDF documents
• Convert tables to markdown format
• Handle multiple tables and large tables
• Support both sync and async operations
• Comprehensive error handling

Implementation

• Added PDFTableExtractTool class
• Added comprehensive test suite
• Added documentation with usage examples
• Implemented proper error handling
• Added type hints and docstrings

Dependencies

Added to pyproject.toml:

• PyMuPDF
• pandas
• tabulate

Testing

All tests passing:

• Basic functionality
• Error handling
• Edge cases
• Async operations

Documentation

• Added detailed README
• Added usage examples
• Added inline documentation

[joaomdmoura]

Looks good but missing a init import if you dont mind adding it :)