[Fix bug] Better for local embedding models #568
Conversation
This file contains 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
When using some local embedding models, they can only use str as input instead of encoded ones. So I decode the chunks back to strs, and now we can use local embedding models.
|
This wonderfully resolves the weight summed to zero issues. Thanks for the PR. Hope the MS team could merge this soon. |
|
This pr is perfectly resolve error in local query,thank you very much. |
|
This wonderfully resolves the weight summed to zero issues. Thanks for the PR. Hope the MS team could merge this soon. |
|
Hi @lyyf2002 Thanks for your contribution! |
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Outdated suggestions cannot be applied.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 pull request adds functionality to decode chunks back to strings, enabling the use of local embedding models that only accept string inputs.
Related Issues
#451
#528
Proposed Changes
Checklist
Additional Notes
These changes ensure compatibility with local embedding models that require string inputs, enhancing the overall functionality and flexibility of the system.