[GH-ISSUE #4377] Request to adapt OpenAI’s GPT-4 vision API #64771

Closed
opened 2026-05-03 18:45:33 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @heshengtao on GitHub (May 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4377

Thank you very much ollama for making it easy for us.
When I am using LLaMA, I want to invoke LLaMA’s visual capabilities. However, following OpenAI’s request method does not allow the model to see the image; the model thinks I have only entered a JSON string containing the image encoding.

Originally created by @heshengtao on GitHub (May 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4377 Thank you very much ollama for making it easy for us. When I am using LLaMA, I want to invoke LLaMA’s visual capabilities. However, following OpenAI’s request method does not allow the model to see the image; the model thinks I have only entered a JSON string containing the image encoding.
GiteaMirror added the feature request label 2026-05-03 18:45:33 -05:00
Author
Owner

@jmorganca commented on GitHub (Jun 5, 2024):

Merging with #3690

<!-- gh-comment-id:2150351204 --> @jmorganca commented on GitHub (Jun 5, 2024): Merging with #3690
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#64771