Delete handler.py

handler.py

@@ -1,83 +0,0 @@
-from huggingface_hub import hf_hub_download
-import joblib
-import json
-
-class EndpointHandler:
-    def __init__(self, path=""):
-        """
-        Initialize the handler, similar to your CuisineClassifier __init__
-        """
-        print("Initializing CuisineClassifier Handler...")
-        
-        components = ["cuisine_pipeline", "label_encoder"]
-        paths = {}
-
-        print("Loading files from local path...")
-        for name in components:
-            print(f"Loading {name}.joblib...")
-            try:
-                # In Inference Endpoints, files are already local in path
-                full_path = f"{path}/{name}.joblib" if path else f"{name}.joblib"
-                paths[name] = full_path
-                print(f"{name} path set to {full_path}")
-            except Exception as e:
-                print(f"Failed to set path for {name}: {e}")
-                raise
-
-        print("Loading model components with joblib...")
-        try:
-            self.model = joblib.load(paths["cuisine_pipeline"])
-            print("Model loaded.")
-            self.label_encoder = joblib.load(paths["label_encoder"])
-            print("Label encoder loaded.")
-        except Exception as e:
-            print(f"Failed to load components: {e}")
-            raise
-
-        print("Handler initialized successfully.")
-
-    def __call__(self, data):
-        """
-        Handle inference requests
-        Expected input format: 
-        {
-            "inputs": ["salt", "flour", "sugar", "eggs"]
-        }
-        OR
-        {
-            "inputs": "salt flour sugar eggs"
-        }
-        """
-        try:
-            # Extract ingredients from request
-            inputs = data.get("inputs", [])
-            
-            # Handle both list and string inputs
-            if isinstance(inputs, list):
-                ingredients_text = " ".join(inputs)
-            else:
-                ingredients_text = str(inputs)
-            
-            print(f"Processing ingredients: {ingredients_text}")
-            
-            # Use your existing classify logic
-            predicted_class = self.model.predict([ingredients_text])
-            predicted_label = self.label_encoder.inverse_transform(predicted_class)
-            
-            # Get prediction probabilities for confidence scores
-            prediction_proba = self.model.predict_proba([ingredients_text])
-            max_confidence = float(max(prediction_proba[0]))
-            
-            # Return structured response
-            return {
-                "cuisine": predicted_label[0],
-                "confidence": max_confidence,
-                "ingredients_processed": ingredients_text
-            }
-            
-        except Exception as e:
-            return {
-                "error": str(e),
-                "cuisine": None,
-                "confidence": 0.0
-            }