- Refactored the Analyze method in the Vision and OpenAI model to accept a variadic prompt parameter, allowing for optional custom prompts while defaulting to a predefined prompt if none is provided.
- Added multiple test cases in vision_test.go and model_test.go to validate image analysis with default, custom, and empty prompts, ensuring robust functionality and error handling.
- Updated the Model interface to reflect the new prompt handling, improving clarity and usability.
These changes enhance the flexibility of the Vision module, paving the way for improved user experience and functionality in image analysis.
- Deleted the obsolete prompt.md file, streamlining the codebase.
- Added tests for image upload and download functionality using local and S3 storage drivers, ensuring robust handling of image files.
- Implemented image compression during upload for both local and S3 storage, maintaining aspect ratio and limiting dimensions to a maximum size of 1920x1080.
- Enhanced the local and S3 storage drivers to support image compression, improving storage efficiency.
- Updated tests to verify image dimensions and content type after upload and download operations, ensuring data integrity.
- Added several AWS SDK v2 modules to go.mod and go.sum, enhancing cloud service integration capabilities:
- github.com/aws/aws-sdk-go-v2 and its related services (S3, STS, SSO, etc.) for improved AWS functionality.
- Updated indirect dependencies to ensure compatibility and performance improvements.
- This update supports future development involving AWS services, streamlining the integration process.
