Maybe I'm misunderstanding this feature but when I upload an image and ask the AI to tell me what the text in the image says, it says the image is not detected.
This is the response I get:
[img-0] is not an actual image, but rather a placeholder or a syntax error.
It seems that you're trying to reference an image file, but it doesn't exist.
So, there is no text to display in this attachment because it's not a real image!
I guess under the hood the image isn't (can't?) be sent to Ollama to understand but if that's the case, what is the proper way to use the attachment feature?
If it should work, what am I doing wrong?
Originally created by @paulwongx on GitHub (Apr 28, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1833
Maybe I'm misunderstanding this feature but when I upload an image and ask the AI to tell me what the text in the image says, it says the image is not detected.
This is the response I get:
```
[img-0] is not an actual image, but rather a placeholder or a syntax error.
It seems that you're trying to reference an image file, but it doesn't exist.
So, there is no text to display in this attachment because it's not a real image!
```
I guess under the hood the image isn't (can't?) be sent to Ollama to understand but if that's the case, what is the proper way to use the attachment feature?
If it should work, what am I doing wrong?
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @paulwongx on GitHub (Apr 28, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/1833
Maybe I'm misunderstanding this feature but when I upload an image and ask the AI to tell me what the text in the image says, it says the image is not detected.
This is the response I get:
I guess under the hood the image isn't (can't?) be sent to Ollama to understand but if that's the case, what is the proper way to use the attachment feature?
If it should work, what am I doing wrong?