ai-computer-vision
latest
false
- Overview
- Setup and configuration
- Authentication
- Rate limit
- Changing the server endpoint
- Single call for Computer Vision and UiPath Screen OCR requests
- Licensing
- Data storage
AI Computer Vision user guide
Last updated May 11, 2026
Applies to Automation Cloud only.
When both Computer Vision and UiPath Screen OCR are requested for the same screenshot, the two requests are merged into a single server call. Since the requested UI elements and text are found in the same image, we are thus optimizing for both latency and rate-limiting.
The single call endpoint is set to the value of the Computer Vision endpoint, as follows:
| Computer Vision endpoint | UiPath Screen OCR endpoint | Single Call endpoint |
|---|---|---|
| West Europe | West Europe | West Europe |
| West Europe | United States | West Europe |
| United States | United States | United States |
| United States | West Europe | United States |
| Local server | Local server | Local server |
| On-premises | On-premises | On-premises |
| Local server/On-premises | Any cloud endpoint (WE/US) | N/A |
| Any cloud endpoint (WE/US) | Local server/On-premises | N/A |
| Local server | On-premises | N/A |
| On-premises | Local server | N/A |
The single-call logic is only applied if both defined Computer Vision and UiPath Screen OCR endpoints are either:
- UiPath cloud servers
- Local server
- On-premises