back to changelog

Vision Capabilities In Preview

Vision capabilities are now available on advanced models such as GPT4o and GPT4-Turbo, seamlessly integrated into major messaging platforms.

We are excited to announce the preview release of our vision capabilities, a significant enhancement to our technology portfolio. The new vision features are now available on advanced models, including GPT4o and GPT4-Turbo, and have been seamlessly integrated into all major messaging platforms such as Telegram, WhatsApp, and Facebook Messenger.

For the first time, users on these messaging platforms can utilize enhanced file support, allowing them to upload files directly into conversations, maintaining a seamless flow and context in interactions. This integration facilitates a more dynamic and interactive user experience, transforming how users and businesses engage through AI-driven communications.

Moreover, Chatbotkit is proud to introduce the "Skillset Action: View" feature. This innovative addition enables the integration of vision capabilities into any model, including more cost-effective options such as GPT3.5-Turbo. This makes Chatbotkit's vision technology one of the most affordable and accessible solutions in the market, democratizing advanced AI capabilities for a wider range of users and applications.

These new capabilities mark a significant milestone in our commitment to enhancing the functionality and accessibility of our AI models. By integrating vision features across our platform, we are not only expanding the utility of our chatbots but also ensuring that advanced AI tools are more accessible and practical for everyone.

All new features are currently in the preview stage, and Chatbotkit is dedicated to refining these capabilities based on user feedback and further development. More updates and enhancements are anticipated as the company continues to innovate and lead in the AI chatbot space.