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

Add one level list nesting for embeddings #8936

Merged
merged 1 commit into from
Aug 9, 2024
Merged

Conversation

gelim
Copy link
Contributor

@gelim gelim commented Aug 8, 2024

This is to support OpenAI compatible clients querying embeddings with "input": [[1, 2, 3]].
See issue #8887

@ggerganov ggerganov merged commit daef3ab into ggerganov:master Aug 9, 2024
53 checks passed
@gelim
Copy link
Contributor Author

gelim commented Aug 9, 2024

This is actually not enough. I found out situation where the client is POSTing to /v1/embeddings with

"input":[[1, 2, 3], [4, 5, 6]]

I have no idea what this brings to split in chunks like this the input data.
This PR in case of previous data sent will just make crash llama-server.

arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 15, 2024
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants