Modernize dependencies, remove DeepSeek support, and add dynamic model detection

[iamarunbrahma]

What does this PR do?

This PR introduces a significant refactor that modernizes the vision-parse library with improved architecture, updated dependencies, and streamlined model support. The changes focus on enhancing performance, maintainability, and user experience while removing deprecated features.

• Addresses technical debt and dependency modernization
• Removes DeepSeek model support and related code
• Introduces dynamic vision model discovery with ModelDetector class
• Updates Gemini model support to newer 2.5 versions
• Replaces PyMuPDF with pypdfium2 for better PDF processing
• Enhances concurrency support and LLM client initialization

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Ran make lint and make format to handle lint / formatting issues.
• Ran make test to run relevant tests scripts.
• Read the contributor guidelines.
• Wrote necessary unit or integration tests.