Allow image input

Created on 4 December 2024, 8 months ago

Problem/Motivation

Allow so you can use images as input as well to agents. If the agent uses an LLM that does not support vision, it will fail with a message that it can't look at the image.

Proposed resolution

Add so that the task files that are images are loaded into the AI call.
Make it possible to use images on the AI Agent Explorer.

Remaining tasks

User interface changes

API changes

Data model changes

✨ Feature request

Status

Active

Version

1.0

Component

Code

Created by

🇩🇪Germany marcus_johansson

Live updates comments and jobs are added and updated live.

Comments & Activities

Issue created by @marcus_johansson
Comment 8 months ago →
System Message

marcus_johansson → committed 0a266cb3 on 1.0.x
Issue #3491662 by marcus_johansson: Allow image input
Comment 8 months ago →
🇩🇪Germany marcus_johansson
Comment 8 months ago →
System Message
Automatically closed - issue fixed for 2 weeks with no activity.
Issue was unassigned.
Status changed to Fixed 6 days ago8:48pm 29 July 2025
Comment 6 days ago →
🇺🇸United States Kristen Pol Santa Cruz, CA, USA
unassigning

contrib.social Blog FAQ Discussions

Production build 0.71.5 2024