Knowledgebase embeddings #2158
Open
Knowledgebase embeddings #2158
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
Contributor
Author
|
I still need to write the tests, but I am sharing the PR already to get feedbacks on the implementation. Little note: You will see that in the load methods you can select another llm or embedding client than the one that was used to generate the KnowledgeBase. I added this purely to add flexibility and improve developer experience, but it was not necessary nor asked in the issue. |
Contributor
Author
|
TODO
|
Member
davidberenstein1957
left a comment
davidberenstein1957
left a comment
There was a problem hiding this comment.
Hi @GTimothee, this already looks nice. I left some comments to improve some things..
| Hugging Face token for authentication. If None, will use local token. | ||
| private : bool | ||
| Whether to make the repo private or public. | ||
| """ |
Member
There was a problem hiding this comment.
should we also pass kwargs for the push to hub/upload file etc?
Comment on lines
401
to
409
| kb = cls( | ||
| data=data, | ||
| columns=config.get("columns"), | ||
| llm_client=llm_client, | ||
| embedding_model=embedding_model, | ||
| chunk_size=config.get("chunk_size", 2048), | ||
| seed=config.get("seed"), | ||
| min_topic_size=config.get("min_topic_size"), | ||
| ) |
Member
There was a problem hiding this comment.
Doesn't this already create the embeddings during initialisation?
Co-authored-by: David Berenstein <david.m.berenstein@gmail.com>
Co-authored-by: David Berenstein <david.m.berenstein@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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
Related Issue
#2145
Type of Change
It is an improvement as it avoids embeddings to be recomputed.
It is a new feature because we can now save/load to/from disk and hugginface hub.
Checklist
CODE_OF_CONDUCT.mddocument.CONTRIBUTING.mdguide.pdm.lockrunningpdm update-lock(only applicable whenpyproject.tomlhas beenmodified)