Update app.py

app.py

@@ -5,6 +5,7 @@ import torch
 import numpy as np
 import json
 import logging
+import requests
 import os
 
 # Configure Logging
@@ -20,38 +21,30 @@ except Exception as e:
     logging.error(f"❌ Failed to load model: {str(e)}")
     raise RuntimeError("Failed to load the model. Please check the logs for details.")
 
-# Load or Create Disease Treatment Database
-disease_treatments_file = "disease_treatments.json"
+# Gemini API Key
+GEMINI_API_KEY = os.getenv("GEMINI_API_KEY", "AIzaSyDaWXCixp-KcO63-lCtCsFbjyXEIFsNV6k")
 
-if not os.path.exists(disease_treatments_file):
-    logging.warning("⚠️ Treatment database file not found. Creating a default one.")
-    default_treatments = {
-        "Powdery Mildew": "Use fungicides like sulfur or neem oil.",
-        "Leaf Blight": "Apply copper-based fungicides.",
-        "Rust": "Use resistant varieties.",
-        "Healthy": "No disease detected!",
-    }
-    with open(disease_treatments_file, "w") as file:
-        json.dump(default_treatments, file)
-    logging.info("✅ Created default 'disease_treatments.json' file.")
-
-# Load Treatments
-with open(disease_treatments_file, "r") as file:
-    disease_treatments = json.load(file)
-    logging.info("✅ Treatment database loaded successfully.")
-
-# Image Validation
-def validate_image(image):
-    if image.size[0] < 64 or image.size[1] < 64:
-        raise ValueError("⚠️ Image is too small. Please upload an image of at least 64x64 pixels.")
-    return image
+# Function to Get AI-Powered Treatment Suggestions
+def get_treatment_suggestions(disease_name):
+    prompt = f"Provide detailed organic and chemical treatment options, including dosage and preventive care, for {disease_name} in crops."
+    url = "https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateText"
+    headers = {"Content-Type": "application/json"}
+    data = {"prompt": prompt, "temperature": 0.7, "max_tokens": 250}
+    params = {"key": GEMINI_API_KEY}
+    try:
+        response = requests.post(url, headers=headers, json=data, params=params)
+        if response.status_code == 200:
+            return response.json().get("candidates", [{}])[0].get("output", "No treatment suggestions found.")
+        else:
+            return "Failed to fetch treatment suggestions."
+    except Exception as e:
+        logging.error(f"Error fetching treatment suggestions: {str(e)}")
+        return "Error retrieving treatment details."
 
-# Prediction Function
+# Define Prediction Function
 def predict(image):
     try:
         image = Image.fromarray(np.uint8(image)).convert("RGB")
-        validate_image(image)
-        
         inputs = processor(images=image, return_tensors="pt")
         with torch.no_grad():
             outputs = model(**inputs)
@@ -59,9 +52,10 @@ def predict(image):
         predicted_class_idx = logits.argmax(-1).item()
         predicted_label = model.config.id2label[predicted_class_idx]
         
-        treatment = disease_treatments.get(predicted_label, "No treatment information available for this disease.")
+        # Get AI-generated treatment suggestions
+        treatment = get_treatment_suggestions(predicted_label)
+        
         return f"Predicted Disease: {predicted_label}\nTreatment: {treatment}"
-    
     except Exception as e:
         logging.error(f"Prediction failed: {str(e)}")
         return f"❌ Prediction failed: {str(e)}"
@@ -71,10 +65,10 @@ iface = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="numpy", label="Upload or capture plant image"),
     outputs=gr.Textbox(label="Result"),
-    title="Plant Disease Detector",
-    description="Upload a plant leaf image to detect diseases and get 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",
 )
 
 # Launch Gradio App
-iface.launch(share=True)  # No fixed port to avoid conflicts
+iface.launch()