upstream-archive/fastembed
1
0
Fork 0
mirror of https://github.com/qdrant/fastembed.git synced 2026-07-23 11:20:51 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix: check lowercase model name for warnings (#523)

Browse Source
This commit is contained in:
George
2025-05-19 14:49:12 +04:00
committed by GitHub
parent c85e8c278f
commit 4736f46548
2 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
fastembed/sparse/sparse_text_embedding.py
View File

@@ -62,7 +62,7 @@ class SparseTextEmbedding(SparseTextEmbeddingBase):
**kwargs: Any,
):
super().__init__(model_name, cache_dir, threads, **kwargs)
if model_name == "prithvida/Splade_PP_en_v1":
if model_name.lower() == "prithvida/Splade_PP_en_v1".lower():
warnings.warn(
"The right spelling is prithivida/Splade_PP_en_v1. "
"Support of this name will be removed soon, please fix the model_name",

14
fastembed/text/text_embedding.py
View File

@@ -55,7 +55,7 @@ class TextEmbedding(TextEmbeddingBase):
) -> None:
registered_models = cls._list_supported_models()
for registered_model in registered_models:
if model == registered_model.model:
if model.lower() == registered_model.model.lower():
raise ValueError(
f"Model {model} is already registered in TextEmbedding, if you still want to add this model, "
f"please use another model name"
@@ -88,18 +88,18 @@ class TextEmbedding(TextEmbeddingBase):
**kwargs: Any,
):
super().__init__(model_name, cache_dir, threads, **kwargs)
if model_name == "nomic-ai/nomic-embed-text-v1.5-Q":
if model_name.lower() == "nomic-ai/nomic-embed-text-v1.5-Q".lower():
warnings.warn(
"The model 'nomic-ai/nomic-embed-text-v1.5-Q' has been updated on HuggingFace. Please review "
"the latest documentation on HF and release notes to ensure compatibility with your workflow. ",
UserWarning,
stacklevel=2,
)
if model_name in {
"sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
"thenlper/gte-large",
"intfloat/multilingual-e5-large",
"sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
if model_name.lower() in {
"sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2".lower(),
"thenlper/gte-large".lower(),
"intfloat/multilingual-e5-large".lower(),
"sentence-transformers/paraphrase-multilingual-mpnet-base-v2".lower(),
}:
warnings.warn(
f"The model {model_name} now uses mean pooling instead of CLS embedding. "