Skip to content

fix case insensitive lookup for custom text models #645

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
CODING-DARSH wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix case insensitive lookup for custom text models #645

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions fastembed/text/custom_text_embedding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,8 +50,10 @@ def __init__(
specific_model_path=specific_model_path,
**kwargs,
)
self._pooling = self.POSTPROCESSING_MAPPING[model_name].pooling
self._normalization = self.POSTPROCESSING_MAPPING[model_name].normalization
self._pooling = self.POSTPROCESSING_MAPPING[self.model_description.model].pooling
self._normalization = self.POSTPROCESSING_MAPPING[
self.model_description.model
].normalization

@classmethod
def _list_supported_models(cls) -> list[DenseModelDescription]:
Expand Down
19 changes: 19 additions & 0 deletions tests/test_custom_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,6 +179,25 @@ def test_mock_add_custom_models():
CustomTextEmbedding.POSTPROCESSING_MAPPING.clear()


def test_custom_text_model_lookup_is_case_insensitive():
model_name = "Org/Model"

TextEmbedding.add_custom_model(
model_name,
pooling=PoolingType.MEAN,
normalization=True,
sources=ModelSource(hf="artificial"),
dim=5,
size_in_gb=0.1,
)

model = TextEmbedding("org/model", lazy_load=True, specific_model_path="./")

assert isinstance(model.model, CustomTextEmbedding)
assert model.model._pooling == PoolingType.MEAN
assert model.model._normalization is True


def test_do_not_add_existing_model():
existing_base_model = "sentence-transformers/all-MiniLM-L6-v2"
custom_model_name = "intfloat/multilingual-e5-small"
Expand Down