Skip to content

refactor: use token inSentenceTransformersDiversityRanker #9126

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

Merged
merged 5 commits into from
Mar 28, 2025
Merged

refactor: use token inSentenceTransformersDiversityRanker #9126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
ad87fe8
chore: use token in SASEvaluator and SentenceTransformersDiversityRanker
anakin87 Mar 27, 2025
64e16ca
directly pass token to CrossEncoder
anakin87 Mar 28, 2025
d96627d
Merge branch 'main' into replace-use-auth-token
anakin87 Mar 28, 2025
b1dec57
restrict scope to SentenceTransformersDiversityRanker
anakin87 Mar 28, 2025
65275b8
Merge branch 'replace-use-auth-token' of https://github.com/deepset-a…
anakin87 Mar 28, 2025
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
2 changes: 1 addition & 1 deletion haystack/components/rankers/sentence_transformers_diversity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -199,7 +199,7 @@ def warm_up(self):
self.model = SentenceTransformer(
model_name_or_path=self.model_name_or_path,
device=self.device.to_torch_str(),
use_auth_token=self.token.resolve_value() if self.token else None,
token=self.token.resolve_value() if self.token else None,
model_kwargs=self.model_kwargs,
tokenizer_kwargs=self.tokenizer_kwargs,
config_kwargs=self.config_kwargs,
Expand Down
5 changes: 5 additions & 0 deletions releasenotes/notes/diversity-ranker-hf-toke-8dcb6889ff625948.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
enhancements:
- |
Updated `SentenceTransformersDiversityRanker` to use the `token` parameter internally instead
of the deprecated `use_auth_token`. The public API of this component already utilizes `token`.
8 changes: 4 additions & 4 deletions test/components/rankers/test_sentence_transformers_diversity.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -290,7 +290,7 @@ def test_warm_up(self, similarity, monkeypatch):
mock_model_class.assert_called_once_with(
model_name_or_path="mock_model_name",
device=ComponentDevice.resolve_device(None).to_torch_str(),
use_auth_token=None,
token=None,
model_kwargs=None,
tokenizer_kwargs=None,
config_kwargs=None,
Expand Down Expand Up @@ -740,7 +740,7 @@ def test_model_onnx_backend(self, mocked_sentence_transformer):
mocked_sentence_transformer.assert_called_once_with(
model_name_or_path="sentence-transformers/all-MiniLM-L6-v2",
device="cpu",
use_auth_token=None,
token=None,
model_kwargs={"file_name": "onnx/model.onnx"},
tokenizer_kwargs=None,
config_kwargs=None,
Expand All @@ -761,7 +761,7 @@ def test_model_openvino_backend(self, mocked_sentence_transformer):
mocked_sentence_transformer.assert_called_once_with(
model_name_or_path="sentence-transformers/all-MiniLM-L6-v2",
device="cpu",
use_auth_token=None,
token=None,
model_kwargs={"file_name": "openvino/openvino_model.xml"},
tokenizer_kwargs=None,
config_kwargs=None,
Expand All @@ -782,7 +782,7 @@ def test_dtype_on_gpu(self, mocked_sentence_transformer, model_kwargs):
mocked_sentence_transformer.assert_called_once_with(
model_name_or_path="sentence-transformers/all-MiniLM-L6-v2",
device="cuda:0",
use_auth_token=None,
token=None,
model_kwargs=model_kwargs,
tokenizer_kwargs=None,
config_kwargs=None,
Expand Down
Loading