[Feature Request]I'd like to see Foundation Model Parsing functionality added

## Describe the solution you'd like
I would like to update the functionality from Advanced Parsing to Foundation Model Parsing so that I can respond with image files.

## Why the solution needed
Using Foundation Model Parsing allows for more visual answers and improves user satisfaction.
In addition, the model can also use Claude3.5sonet, which is expected to improve accuracy.

## Additional context

Add any other context or screenshots about the feature request here.

## Implementation feasibility

Are you willing to collaborate with us to discuss the solution, decide on the approach, and assist with the implementation?

- [ ] Yes, I am able to implement the feature and create a pull request.
- [x] No, I am unable to implement the feature, but I am open to discussing the solution.

The issue names no files, tests, or entry points. Start by locating the existing Advanced Parsing integration and the AWS model configuration, then determine how Foundation Model Parsing and Claude 3.5 Sonnet should produce image-file responses; done means the feature works end to end with visual answers.

Written by the indexing model from the issue text.