Update app.py

app.py

@@ -6,11 +6,11 @@ import torch
 import numpy as np
 import requests
 import logging
-from dotenv import load_dotenv  # Load .env file
 
-# Load environment variables
-load_dotenv()
+# Load Hugging Face API Key from Secrets
 HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
+if not HUGGINGFACE_API_KEY:
+    raise ValueError("❌ Missing Hugging Face API Key. Please set it in Hugging Face Secrets.")
 
 # Configure Logging
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
@@ -33,12 +33,16 @@ def get_treatment_suggestions(disease_name):
 
     try:
         response = requests.post(url, headers=headers, json=data)
-        if response.status_code == 200:
-            return response.json()[0]["generated_text"]
+        response_data = response.json()
+
+        if response.status_code == 200 and isinstance(response_data, list):
+            return response_data[0].get("generated_text", "No treatment information found.")
         else:
-            return f"API Error: {response.status_code}"
+            logging.error(f"API Error {response.status_code}: {response_data}")
+            return f"API Error {response.status_code}: {response_data.get('error', 'Unknown error')}"
     except Exception as e:
-        return "Error retrieving treatment details."
+        logging.error(f"Error fetching treatment suggestions: {str(e)}")
+        return "❌ Error retrieving treatment details."
 
 # Define Prediction Function
 def predict(image):
@@ -50,11 +54,11 @@ def predict(image):
         logits = outputs.logits
         predicted_class_idx = logits.argmax(-1).item()
         predicted_label = model.config.id2label[predicted_class_idx]
-        
+
         # Get AI-generated treatment suggestions
         treatment = get_treatment_suggestions(predicted_label)
-        
-        return f"Predicted Disease: {predicted_label}\nTreatment: {treatment}"
+
+        return f"🌱 **Predicted Disease:** {predicted_label}\n💊 **Treatment:** {treatment}"
     except Exception as e:
         logging.error(f"Prediction failed: {str(e)}")
         return f"❌ Prediction failed: {str(e)}"
@@ -64,8 +68,8 @@ iface = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="numpy", label="Upload or capture plant image"),
     outputs=gr.Textbox(label="Result"),
-    title="AI-Powered Plant Disease Detector",
-    description="Upload a plant leaf image to detect diseases and get AI-powered treatment suggestions.",
+    title="🌿 AI-Powered Plant Disease Detector",
+    description="📷 Upload a plant leaf image to detect diseases and get AI-powered treatment suggestions.",
     allow_flagging="never",
 )