Normalize string formatting and CLI logging

Author: ghukill

embeddings/cli.py

@@ -62,26 +62,17 @@ def ping() -> None:
 )
 def download_model(model_uri: str, output: Path) -> None:
     """Download a model from HuggingFace and save as zip file."""
-    try:
-        model_class = get_model_class(model_uri)
-    except ValueError as e:
-        logger.exception("Unknown model URI: %s", model_uri)
-        raise click.ClickException(str(e)) from e
-
-    logger.info("Downloading model: %s", model_uri)
+    # load embedding model class
+    model_class = get_model_class(model_uri)
     model = model_class(model_uri)
 
-    try:
-        result_path = model.download(output)
-        logger.info("Model downloaded successfully to: %s", result_path)
-        click.echo(f"Model saved to: {result_path}")
-    except NotImplementedError as e:
-        logger.exception("Download not yet implemented for model: %s", model_uri)
-        raise click.ClickException(str(e)) from e
-    except Exception as e:
-        logger.exception("Failed to download model: %s", model_uri)
-        msg = f"Download failed: {e}"
-        raise click.ClickException(msg) from e
+    # download model assets
+    logger.info(f"Downloading model: {model_uri}")
+    result_path = model.download(output)
+
+    message = f"Model downloaded and saved to: {result_path}"
+    logger.info(message)
+    click.echo(result_path)
 
 
 @main.command()
@@ -90,9 +81,8 @@ def download_model(model_uri: str, output: Path) -> None:
     required=True,
     help="HuggingFace model URI (e.g., 'org/model-name')",
 )
-def create_embeddings(model_uri: str) -> None:
-    """Create embeddings."""
-    logger.info("create-embeddings command called with model: %s", model_uri)
+def create_embeddings(_model_uri: str) -> None:
+    # TODO: docstring # noqa: FIX002
     raise NotImplementedError
 
 

embeddings/models/registry.py

@@ -1,8 +1,12 @@
 """Registry mapping model URIs to model classes."""
 
+import logging
+
 from embeddings.models.base import BaseEmbeddingModel
 from embeddings.models.os_neural_sparse_doc_v3_gte import OSNeuralSparseDocV3GTE
 
+logger = logging.getLogger(__name__)
+
 MODEL_REGISTRY: dict[str, type[BaseEmbeddingModel]] = {
     "opensearch-project/opensearch-neural-sparse-encoding-doc-v3-gte": (
         OSNeuralSparseDocV3GTE
@@ -22,5 +26,6 @@ def get_model_class(model_uri: str) -> type[BaseEmbeddingModel]:
     if model_uri not in MODEL_REGISTRY:
         available = ", ".join(sorted(MODEL_REGISTRY.keys()))
         msg = f"Unknown model URI: {model_uri}. Available models: {available}"
+        logger.error(msg)
         raise ValueError(msg)
     return MODEL_REGISTRY[model_uri]

pyproject.toml

@@ -63,6 +63,8 @@ ignore = [
     "PLR0913", 
     "PLR0915",
     "S321",
+    "TD002",
+    "TD003",
 ]
 
 # allow autofix behavior for specified rules

tests/test_cli.py

@@ -16,12 +16,12 @@ def test_cli_debug_logging(caplog, runner):
     assert "pong" in result.output
 
 
-def test_download_model_unknown_uri(runner):
+def test_download_model_unknown_uri(caplog, runner):
     result = runner.invoke(
         main, ["download-model", "--model-uri", "unknown/model", "--output", "out.zip"]
     )
     assert result.exit_code != 0
-    assert "Unknown model URI" in result.output
+    assert "Unknown model URI" in caplog.text
 
 
 def test_download_model_not_implemented(caplog, runner):