chore: replace semver dependency with packaging (#1311)

Fixes #1296 per title. See
https://github.com/lancedb/lancedb/pull/1298#discussion_r1603931457 Cc
@wjones127

---------

Co-authored-by: Will Jones <willjones127@gmail.com>

python/python/lancedb/embeddings/bedrock.py

@@ -74,7 +74,7 @@ class BedRockText(TextEmbeddingFunction):
     profile_name: Union[str, None] = None
     role_session_name: str = "lancedb-embeddings"
 
-    if PYDANTIC_VERSION < (2, 0):  # Pydantic 1.x compat
+    if PYDANTIC_VERSION.major < 2:  # Pydantic 1.x compat
 
         class Config:
             keep_untouched = (cached_property,)

python/python/lancedb/embeddings/gemini_text.py

@@ -90,7 +90,7 @@ class GeminiText(TextEmbeddingFunction):
     query_task_type: str = "retrieval_query"
     source_task_type: str = "retrieval_document"
 
-    if PYDANTIC_VERSION < (2, 0):  # Pydantic 1.x compat
+    if PYDANTIC_VERSION.major < 2:  # Pydantic 1.x compat
 
         class Config:
             keep_untouched = (cached_property,)

python/python/lancedb/embeddings/imagebind.py

@@ -40,7 +40,7 @@ class ImageBindEmbeddings(EmbeddingFunction):
     device: str = "cpu"
     normalize: bool = False
 
-    if PYDANTIC_VERSION < (2, 0):  # Pydantic 1.x compat
+    if PYDANTIC_VERSION.major < 2:  # Pydantic 1.x compat
 
         class Config:
             keep_untouched = (cached_property,)

python/python/lancedb/embeddings/transformers.py

@@ -54,7 +54,7 @@ class TransformersEmbeddingFunction(EmbeddingFunction):
         self._tokenizer = transformers.AutoTokenizer.from_pretrained(self.name)
         self._model = transformers.AutoModel.from_pretrained(self.name)
 
-    if PYDANTIC_VERSION < (2, 0):  # Pydantic 1.x compat
+    if PYDANTIC_VERSION.major < 2:  # Pydantic 1.x compat
 
         class Config:
             keep_untouched = (cached_property,)

python/python/lancedb/pydantic.py

@@ -35,13 +35,13 @@ from typing import (
 import numpy as np
 import pyarrow as pa
 import pydantic
-import semver
+from packaging.version import Version
 
-PYDANTIC_VERSION = semver.parse_version_info(pydantic.__version__)
+PYDANTIC_VERSION = Version(pydantic.__version__)
 try:
     from pydantic_core import CoreSchema, core_schema
 except ImportError:
-    if PYDANTIC_VERSION >= (2,):
+    if PYDANTIC_VERSION.major >= 2:
         raise
 
 if TYPE_CHECKING:
@@ -144,7 +144,7 @@ def Vector(
                 raise TypeError("A list of numbers or numpy.ndarray is needed")
             return cls(v)
 
-        if PYDANTIC_VERSION < (2, 0):
+        if PYDANTIC_VERSION.major < 2:
 
             @classmethod
             def __modify_schema__(cls, field_schema: Dict[str, Any]):

python/python/lancedb/rerankers/cohere.py

@@ -1,5 +1,5 @@
 import os
-import semver
+from packaging.version import Version
 from functools import cached_property
 from typing import Union
 
@@ -44,9 +44,8 @@ class CohereReranker(Reranker):
     def _client(self):
         cohere = attempt_import_or_raise("cohere")
         # ensure version is at least 0.5.0
-        if (
-            hasattr(cohere, "__version__")
-            and semver.compare(cohere.__version__, "5.0.0") < 0
+        if hasattr(cohere, "__version__") and Version(cohere.__version__) < Version(
+            "0.5.0"
         ):
             raise ValueError(
                 f"cohere version must be at least 0.5.0, found {cohere.__version__}"

python/python/tests/test_pydantic.py

@@ -178,7 +178,7 @@ def test_fixed_size_list_field():
         li: List[int]
 
     data = TestModel(vec=list(range(16)), li=[1, 2, 3])
-    if PYDANTIC_VERSION >= (2,):
+    if PYDANTIC_VERSION.major >= 2:
         assert json.loads(data.model_dump_json()) == {
             "vec": list(range(16)),
             "li": [1, 2, 3],
@@ -197,7 +197,7 @@ def test_fixed_size_list_field():
         ]
     )
 
-    if PYDANTIC_VERSION >= (2,):
+    if PYDANTIC_VERSION.major >= 2:
         json_schema = TestModel.model_json_schema()
     else:
         json_schema = TestModel.schema()