UiPath Computer Vision is a deep-learning-based capability that analyses graphical user interfaces (GUIs) across virtual desktops, Citrix, and remote terminal sessions where standard UI element selectors are unavailable. Because the underlying neural network models demand high parallel-compute processing throughput to execute real-time image segmentation and OCR inference, installing Computer Vision within Automation Suite requires a dedicated agent node provisioned with specialized GPU support. UiPath requires NVIDIA GPUs (such as Tesla T4, A10, or newer enterprise Ampere architectures) equipped with the official NVIDIA container toolkit and drivers installed at the host operating system level. To prevent standard product pods or control-plane services from exhausting GPU memory, this node is tainted so that only Computer Vision and specialized AI workloads tolerate and schedule onto it. Attempting to run Computer Vision purely on generic CPU-bound agent nodes is unsupported due to severe inference latency and pod scheduling constraints. (Reference: UiPath Automation Suite Sizing and Hardware Requirements – Specialized GPU Nodes).
===============
Contribute your Thoughts:
Chosen Answer:
This is a voting comment (?). You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Submit