We now support VLMs in smolagents!

smolagents now supports vision language models (VLMs) by allowing images to be passed to the agent at start or dynamically via callbacks, enabling use cases like autonomous web browsing.

From the source
We have added vision support to smolagents, which unlocks the use of vision language models in agentic pipelines natively.
huggingface.co

Visit source ↗huggingface.co

Announced: 24 Jan 2025 00:00 UTC
Detected: 03 Aug 2026 21:12 UTC (+556d after)

Other stories

GitHub · 31 AugGitHub Copilot in VS Code, August 2026 releasesCapability change

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Amazon · 28 AugSpreading the load: How Salesforce met Multi-AZ HA with SageMaker Inference ComponentsCapability change

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change

Amazon · 27 AugBuild agentic creative workflows with Amazon Quick and falCapability change