n0x29a fa2205115d Fix: Normalize tokens to lowercase before checking stopwords in BM25 (#337) ...

* Fix: Normalize tokens to lowercase before checking stopwords in BM25

* Test: Normalize tokens to lowercase before checking stopwords in BM25

* Test Fix test_multilanguage: in "Je suis au lit", the "Je" should be skipped because it in the stopwords.

* chore: apply ruff

---------

Co-authored-by: H4-8ZSI <H4-8ZSI@EXAMPLE.COM>

2024-09-06 11:42:00 +02:00

..

misc

Clip (#219)

2024-05-09 11:12:25 +02:00

__init__.py

Fix to avoid overfloat and get rid of model_max_length (#319)

2024-08-14 15:59:22 +03:00

config.py

Clip (#219)

2024-05-09 11:12:25 +02:00

profiling.py

MiniLM fix (#275)

2024-06-14 16:42:31 +03:00

test_attention_embeddings.py

Fix: Normalize tokens to lowercase before checking stopwords in BM25 (#337)

2024-09-06 11:42:00 +02:00

test_image_onnx_embeddings.py

Opened images support (#315)

2024-07-31 13:23:17 +03:00

test_late_interaction_embeddings.py

answerdotai/answerai-colbert-small-v1 support added (#330)

2024-08-23 18:17:39 +02:00

test_sparse_embeddings.py

Fix: Normalize tokens to lowercase before checking stopwords in BM25 (#337)

2024-09-06 11:42:00 +02:00

test_text_onnx_embeddings.py

Fix to avoid overfloat and get rid of model_max_length (#319)

2024-08-14 15:59:22 +03:00