Add Open Terminal image analysis to Vision Bridge - #84
Open
d3cker wants to merge 3 commits into
Open
Conversation
Owner
|
will have time to review soon |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Summary
This PR adds analyze_terminal_image, allowing Vision Bridge to inspect images created or stored in the currently connected Open Terminal.
It also adds system instructions that tell the model when to use:
analyze_imagefor images attached to the conversation.analyze_terminal_imagefor image files located in Open Terminal.Motivation
Images generated through the Open WebUI -> Open Terminal workflow are terminal files, not chat attachments with a
file_id. As a result,analyze_imagecould not resolve them: the bridge returned a missing-image error and the workflow stalled.The new tool reads the image directly from the connected terminal and forwards it to the configured vision model. This lets the text-only model continue the workflow and visually verify generated or modified images.
Testing
Execute the following prompt:
Contributor License Agreement (REQUIRED)
By submitting this pull request, I agree to the following terms:
By submitting my contributions to this repository in any form, I grant Classic298 a perpetual, worldwide, irrevocable, royalty-free license, under copyright and patent, to use, modify, distribute, sublicense, and commercialize my work under any terms they choose, both now and in the future.
I represent that my contributions are my original work (or that I have sufficient rights to grant this license) and that I have the authority to enter into this agreement.
To the fullest extent permitted by law, my contributions are provided on an "as is" basis, with no warranties or guarantees of any kind, and I disclaim any liability for any issues or damages arising from their use or incorporation into the project, regardless of the type of legal claim.