We now support VLMs in smolagents!

Smolagents has announced support for Vision-Language Models (VLMs), enabling the integration of multimodal capabilities within their framework. This update allows practitioners to utilize models that combine visual and textual understanding, enhancing the versatility of agent-based applications. The integration of VLMs is expected to streamline the development of AI systems that require both visual perception and language processing, thus expanding the potential use cases for smolagents in real-world applications.