fix(llama-cpp): correctly calculate embeddings #6259
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
✅ Deploy Preview for localai ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
c1da49d to
a22cf73
Compare
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
a22cf73 to
a7c7757
Compare
2a7d709 to
4d15aa3
Compare
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
4d15aa3 to
efd98bc
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR is to add a test to validate #6257 specifically for the llama.cpp backend. We have this test for sentencetransformers just a couple of lines below, but somehow seems we missed applying it to llama.cppSeems the bug is confirmed. It looks like we did had a regression while we migrated to the new mtmd/context server. We were incorrectly returning always a static embedding vector in the embedding calls with the llama.cpp backend.
Notes for Reviewers
Fixes #6257
Signed commits