Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

GPT 4-turbo does not support images #1774

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

ndroo
Copy link

@ndroo ndroo commented Jun 2, 2024

This fixes #1773

When you try to upload an image on this model it produces a toast error in production today. This prevents images from being selected, same as gpt 3.5.


🚀 This description was created by Ellipsis for commit cad0446

Summary:

This PR disables image input for the GPT 4-turbo model to prevent errors related to unsupported image uploads.

Key points:

  • Changed imageInput from true to false for GPT4Turbo in lib/models/llm/openai-llm-list.ts

Generated with ❤️ by ellipsis.dev

Copy link

@ellipsis-dev ellipsis-dev bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

👍 Looks good to me! Reviewed everything up to cad0446 in 1 minute and 1 seconds

More details
  • Looked at 14 lines of code in 1 files
  • Skipped 0 files when reviewing.
  • Skipped posting 1 drafted comments based on config settings.
1. lib/models/llm/openai-llm-list.ts:28
  • Draft comment:
    The change correctly sets imageInput to false for GPT4Turbo, aligning with the behavior of similar models and resolving the issue as described. No further modifications are needed here.
  • Reason this comment was not posted:
    Confidence changes required: 0%
    The change in the PR is straightforward and directly addresses the issue described. The imageInput property for the GPT4Turbo model is set to false, which aligns with the issue's requirement to prevent image uploads for this model. This change is consistent with the behavior of other models that do not support image inputs, such as GPT4 and GPT3_5Turbo. There are no apparent logical, performance, or security issues with this change. The PR effectively resolves the issue by updating the model configuration to prevent image uploads, which is what the issue requested.

Workflow ID: wflow_Hmg4McRpRiOIJzT2


You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Image upload isnt supported by 4-turbo but UI allows it
1 participant