Upgrade FastEmbed Version #493
Merged
+414
−163
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
✅ Deploy Preview for poetic-froyo-8baba7 ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
joein
requested changes
Feb 15, 2024
qdrant_client/qdrant_fastembed.py
Outdated
| "BAAI/bge-small-en-v1.5": (384, models.Distance.COSINE), | ||
| "BAAI/bge-base-en-v1.5": (768, models.Distance.COSINE), | ||
| "intfloat/multilingual-e5-large": (1024, models.Distance.COSINE), | ||
| } | ||
|
|
||
|
|
||
| class QdrantFastembedMixin(QdrantBase): | ||
| DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en" | ||
| DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en-v1.5" |
There was a problem hiding this comment.
I don't think we can just silently replace the default model
There was a problem hiding this comment.
We need to make at least one major release which warns that we are going to change the model
|
|
||
| SUPPORTED_EMBEDDING_MODELS: Dict[str, Tuple[int, models.Distance]] = { | ||
| "BAAI/bge-base-en": (768, models.Distance.COSINE), |
There was a problem hiding this comment.
we can't just silently remove models which could have already been used by users
2 tasks
joein
force-pushed
the
nirant/upgrade-fastembed-version
branch
from
0803fb5 to
34f6037
Compare
|
We need to fix our tests to run them without fastembed installed as well |
3 tasks
joein
force-pushed
the
nirant/upgrade-fastembed-version
branch
from
510efbc to
9323c0a
Compare
generall
approved these changes
Mar 5, 2024
| "BAAI/bge-small-en-v1.5": (384, models.Distance.COSINE), | ||
| "BAAI/bge-base-en-v1.5": (768, models.Distance.COSINE), | ||
| "intfloat/multilingual-e5-large": (1024, models.Distance.COSINE), | ||
| } | ||
|
|
||
|
|
||
| class AsyncQdrantFastembedMixin(AsyncQdrantBase): | ||
| DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en" | ||
| embedding_models: Dict[str, "DefaultEmbedding"] = {} | ||
| DEFAULT_EMBEDDING_MODEL = "BAAI/bge-small-en-v1.5" |
There was a problem hiding this comment.
I don't feel so good about this change. We should deprecate things, not suddenly disable defaults
joein
approved these changes
Mar 5, 2024
joein
added a commit
that referenced
this pull request
Mar 5, 2024
* Update fastembed to v0.2.1 * chore(qdrant_fastembed.py): update DEFAULT_EMBEDDING_MODEL * fix(fastembed integration): upgrade to latest version * Prefer black over ruff * Prefer black over ruff * Remove hardcoded directory structure from Qdrant Client checks * new: deprecate current default model, deprecate max token length, update fastembed * fix: make embedding_model_name method sync * fix: update poetry lock * refactor: use list_supported_models() (#501) * fix: fix fastembed check * fix: fix fastembed class var assignment * fix: remove fastembed deprecation from qdrant client (#524) --------- Co-authored-by: George Panchuk <[email protected]> Co-authored-by: Anush <[email protected]>
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.
All Submissions:
devbranch. Did you create your branch fromdev?New Feature Submissions:
pre-commitwithpip3 install pre-commitand set up hooks withpre-commit install?Changes to Core Features: