-
Notifications
You must be signed in to change notification settings - Fork 5.5k
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
deprecate modelfile embed command #759
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks good to me. It might be good to leave it open for a few days to see if anyone is directly impacted by this. Even though this is a breaking change, I think it's OK given we're still only at 0.1.x.
- go mod tidy - better deprecation message
Good cleanup, @technovangelist we should couple this with some good embedding examples under |
Embedding in prompt would be useful for multimodal. Llama.cpp now supports Llava 1.5 for image+text. |
Hi @chigkim, thanks for the feedback. That does sound like a useful feature, let's open it as a separate issue for now. |
I appreciate the effort keeping the codebase simple, Ollama is second to none in its elegance. But this was quick work outright removing of the feature within a week without much debate if and how people use it, and is it really not valuable, or maybe it's a fantastic feature on second thought. I am going to miss this feature a lot and was highlighting it to others as an Ollama special treat. It was in daily use. I'd like to bring some more viewpoints to this, as a heavy user who's tried everything I've gotten my hands on:
I'll write this as a new issue so it can be tracked, maybe there's more feedback. Please consider bringing it back. I'm going to park to v0.1.3 tag until new killer features come along. Thanks a lot for the great work! Please ask community opinion with a clear issue headline before deprecating powerful capabilities in a breaking change, and give it a few weeks if not urgent. |
Embeddings in Modelfiles are a convenient idea, allowing the model to be packaged with embeddings created for it specifically, but the user-experience of this implementation isn't up to par.
This change leaves the
/embed
endpoint, but deprecatesEMBED
in the modelfile.Instead of using the Modelfile the right way to do this is with an external tool such as PrivateGPT or LlamaIndex that uses Ollama as the runner.
New behavior:
On create a modelfile with the embed command:
On running a modelfile with the embed command:
On running a modelfile with the embed in the template: