Gemini AI Toolkit v1.3

This major update elevates the Gemini AI Toolkit to a new level of versatility and power, introducing multimodal support that allows seamless integration of text, images, audio, video, documents, code and a variety of inputs. The toolkit now offers a more robust and scalable architecture, featuring enhanced error handling, a sophisticated file management system with caching, and improved user interaction across all interfaces.

Key highlights include:

• New Multimodal class for handling diverse input types in a single request
• Support for commands, like /exit, /clear and /upload
• Comprehensive file handling with caching for optimized performance
• Refined error management providing clear, actionable feedback
• Expanded CLI capabilities supporting advanced multimodal interactions
• Improved safety controls and configuration options

Full Changelog: v1.2.1...v1.3

Gemini AI Toolkit v1.2.1

This update enhances the Gemini AI Toolkit with additional features, improved error handling, and expanded functionality, particularly introducing support for audio inputs and refining multimedia interaction. These improvements aim to make the toolkit more versatile and user-friendly, addressing community feedback and the evolving needs of developers.

Full Changelog: v1.2.0...v1.2.1

Gemini AI Toolkit v1.2.0

This update transforms the Gemini AI Toolkit from a basic API wrapper into a comprehensive, user-friendly, and highly customizable interface for interacting with Google's Gemini API. The changes encompass a complete redesign of the codebase, introducing new functionalities, improving modularization, enhancing user experience, and providing advanced configuration options.