Integration of dense embedding model Snowflake arctic-embed-m-v1.5 #2001
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
|
This is linked to resolving issue #1959 |
lintool
requested changes
Oct 1, 2024
| @@ -362,6 +364,43 @@ def encode(self, query: str, **kwargs): | |||
| return self.get_embedding(inputs) | |||
| else: | |||
| return super().encode(query) | |||
|
|
|||
|
|
|||
| class ArcticQueryEncoder(QueryEncoder): | |||
There was a problem hiding this comment.
Why are there two different ArcticQueryEncoder classes? Here and in encode._artic?
There was a problem hiding this comment.
Yeah that is how the current version of pyserini does for all query encoders. Shivani and I were talking about this too. Maybe we could make a separate issue on this matter?
| @@ -413,6 +452,14 @@ def encode(self, query: str): | |||
| return embeddings.flatten() | |||
| else: | |||
| return super().encode(query) | |||
|
|
|||
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Outdated suggestions cannot be applied.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.
This update integrates the Snowflake arctic-embed-m-v1.5 dense embedding model into the Pyserini toolkit. A new class was developed to support the entire snowflake-series of models, offering a scalable foundation for future expansions, such as additional Snowflake embedding model integrations. This modification is intended to lay the groundwork for smoother integration of future models from the Snowflake series