Add image-to-text support

[andrewfrench]

• [x] I have read and agree to the contributing guidelines.

Is your feature request related to a problem? Please describe. Griptape lacks support for image-to-text workflows.

Describe the solution you'd like Support for image-to-text workflows:

• ImageToTextTask
• ImageToTextEngine
• ImageToText drivers for each supported provider (Textract, OpenAI Vision, etc.)
• Model drivers for providers offering multiple models, if applicable

Describe alternatives you've considered n/a

Additional context n/a