add deprecation warnings

python/python/lancedb/embeddings/gte.py

@@ -2,6 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 
+import warnings
 from typing import List, Union
 
 import numpy as np
@@ -15,6 +16,8 @@ from .utils import weak_lru
 @register("gte-text")
 class GteEmbeddings(TextEmbeddingFunction):
     """
+    Deprecated: GTE embeddings should be used through sentence-transformers.
+
     An embedding function that uses GTE-LARGE MLX format(for Apple silicon devices only)
     as well as the standard cpu/gpu version from: https://huggingface.co/thenlper/gte-large.
 
@@ -61,6 +64,13 @@ class GteEmbeddings(TextEmbeddingFunction):
 
     def __init__(self, **kwargs):
         super().__init__(**kwargs)
+        warnings.warn(
+            "GTE embeddings as a standalone embedding function are deprecated. "
+            "Use the 'sentence-transformers' embedding function with a GTE model "
+            "instead.",
+            DeprecationWarning,
+            stacklevel=3,
+        )
         self._ndims = None
         if kwargs:
             self.mlx = kwargs.get("mlx", False)

python/python/lancedb/embeddings/siglip.py

@@ -6,6 +6,7 @@ import io
 import os
 from typing import TYPE_CHECKING, List, Union
 import urllib.parse as urlparse
+import warnings
 
 import numpy as np
 import pyarrow as pa
@@ -24,6 +25,7 @@ if TYPE_CHECKING:
 
 @register("siglip")
 class SigLipEmbeddings(EmbeddingFunction):
+    # Deprecated: prefer CLIP embeddings via `open-clip`.
     model_name: str = "google/siglip-base-patch16-224"
     device: str = "cpu"
     batch_size: int = 64
@@ -36,6 +38,12 @@ class SigLipEmbeddings(EmbeddingFunction):
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
+        warnings.warn(
+            "SigLip embeddings are deprecated. Use CLIP embeddings via the "
+            "'open-clip' embedding function instead.",
+            DeprecationWarning,
+            stacklevel=3,
+        )
         transformers = attempt_import_or_raise("transformers")
         self._torch = attempt_import_or_raise("torch")