Add test for Vicinity.load_from_hub method

- Implemented a new test case for loading a Vicinity instance from Hugging Face Hub
- Added test to verify the print statement when loading from a repository
- Introduced a constant for the print statement in the Hugging Face integration module
- Updated the print statement to use string formatting for better flexibility

Author: davidberenstein1957

tests/test_vicinity.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import io
+import sys
 from pathlib import Path
 
 import numpy as np
@@ -8,6 +10,7 @@
 
 from vicinity import Vicinity
 from vicinity.datatypes import Backend
+from vicinity.integrations.huggingface import _MODEL_NAME_OR_PATH_PRINT_STATEMENT
 
 BackendType = tuple[Backend, str]
 
@@ -333,3 +336,25 @@ def test_vicinity_evaluate(vicinity_instance: Vicinity, vectors: np.ndarray) ->
     vicinity_instance.backend.arguments.metric = "manhattan"
     with pytest.raises(ValueError):
         vicinity_instance.evaluate(vectors, query_vectors)
+
+
+def test_load_from_hub(vicinity_instance: Vicinity) -> None:
+    """
+    Test Vicinity.load_from_hub.
+
+    :param vicinity_instance: A Vicinity instance.
+    """
+    repo_id = "davidberenstein1957/my-vicinity-repo"
+    expected_print_statement = _MODEL_NAME_OR_PATH_PRINT_STATEMENT.split(":")[0]
+
+    # Capture the output
+    captured_output = io.StringIO()
+    sys.stdout = captured_output
+
+    Vicinity.load_from_hub(repo_id=repo_id)
+
+    # Reset redirect.
+    sys.stdout = sys.__stdout__
+
+    # Check if the expected message is in the output
+    assert expected_print_statement in captured_output.getvalue()

vicinity/integrations/huggingface.py

@@ -17,6 +17,9 @@
 _HUB_IMPORT_ERROR = ImportError(
     "`datasets` and `huggingface_hub` are required to push to the Hugging Face Hub. Please install them with `pip install 'vicinity[huggingface]'`"
 )
+_MODEL_NAME_OR_PATH_PRINT_STATEMENT = (
+    "Embeddings in Vicinity instance were created from model name or path: {model_name_or_path}"
+)
 
 logger = logging.getLogger(__name__)
 
@@ -128,7 +131,7 @@ def load_from_hub(cls, repo_id: str, token: str | None = None, **kwargs: Any) ->
             config = json.load(f)
             model_name_or_path = config.pop("model_name_or_path")
 
-        print(f"Embeddings in Vicinity instance were created from model name or path: {model_name_or_path}")
+        print(_MODEL_NAME_OR_PATH_PRINT_STATEMENT.format(model_name_or_path=model_name_or_path))
         backend_type = Backend(config["backend_type"])
         backend = get_backend_class(backend_type).load(repo_path / "backend")