fix: deprecate outdated files for embedding registry (#3037)

There are old and outdated files in our embedding registry that can
confuse coding agents. This PR deprecates the following files that have
newer, more modern methods to generate such embeddings.

- Deprecate `embeddings/siglip.py` 
- Deprecate `embeddings/gte.py` 

## Why this change?

Per a discussion with @AyushExel, the [embedding registry directory
](1840aa7edc/python/python/lancedb/embeddings)
in the LanceDB repo has a number of outdated files that need to be
deprecated.

See https://github.com/lancedb/docs/issues/85 for the docs gaps that
identified this.
- Add note in `openclip` docs that it can be used for SigLip embeddings,
which it now supports
- Add note in the `sentence-transformers` page that ALL text embedding
models on Hugging Face can be used

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")