Update app.py

app.py

@@ -1,98 +1,75 @@
 import os
+import json
 import gradio as gr
-import torch
 import requests
 import logging
-import numpy as np
 from PIL import Image
-from bs4 import BeautifulSoup
-from transformers import AutoImageProcessor, AutoModelForImageClassification
+import numpy as np
+from io import BytesIO
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# Get API key from environment variables
+PLANT_ID_API_KEY = os.getenv("PLANT_ID_API_KEY")
+
+if not PLANT_ID_API_KEY:
+    raise ValueError("❌ API Key is missing! Set PLANT_ID_API_KEY in Hugging Face Secrets or .env file.")
 
 # Configure Logging
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 
-# Load Model & Processor
-MODEL_NAME = "linkanjarad/mobilenet_v2_1.0_224-plant-disease-identification"
-
-try:
-    processor = AutoImageProcessor.from_pretrained(MODEL_NAME, use_fast=True)
-    model = AutoModelForImageClassification.from_pretrained(MODEL_NAME)
-    logging.info("✅ Model and processor loaded successfully.")
-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.")
+# Plant.id API URL
+PLANT_ID_URL = "https://api.plant.id/v2/health_assessment"
 
-# Function to Fetch Treatment Suggestions from the Internet
-def fetch_treatment_info(disease_name):
+# Function to get disease and treatment information from Plant.id
+def analyze_plant_health(image):
     try:
-        search_url = f"https://www.bing.com/search?q=treatment+for+{disease_name.replace(' ', '+')}+in+plants"
-        headers = {"User-Agent": "Mozilla/5.0"}
-        response = requests.get(search_url, headers=headers)
+        # Convert image to bytes
+        buffered = BytesIO()
+        image.save(buffered, format="JPEG")
+        img_bytes = buffered.getvalue()
 
-        if response.status_code == 200:
-            soup = BeautifulSoup(response.text, "html.parser")
-            snippets = soup.find_all("p")  
-            treatments = [s.text for s in snippets][:3]  
+        # Send request to Plant.id API
+        headers = {"Content-Type": "application/json"}
+        payload = {
+            "images": [f"data:image/jpeg;base64,{img_bytes.decode()}"],
+            "organs": ["leaf"],
+            "api_key": PLANT_ID_API_KEY
+        }
 
-            return "\n".join(treatments) if treatments else "No treatment suggestions found."
-        else:
-            return "Failed to fetch treatment suggestions."
-    except Exception as e:
-        logging.error(f"Error fetching treatment info: {str(e)}")
-        return "Error retrieving treatment details."
+        response = requests.post(PLANT_ID_URL, headers=headers, json=payload)
 
-# Define Prediction Function
-def predict(image):
-    try:
-        image = Image.fromarray(np.uint8(image)).convert("RGB")
-        inputs = processor(images=image, return_tensors="pt")
+        if response.status_code != 200:
+            return f"❌ API Error: {response.text}"
+
+        data = response.json()
+        
+        if "health_assessment" not in data:
+            return "⚠️ No disease detected or insufficient data."
 
-        with torch.no_grad():
-            outputs = model(**inputs)
-        logits = outputs.logits
-        predicted_class_idx = logits.argmax(-1).item()
-        confidence = torch.nn.functional.softmax(logits, dim=-1)[0][predicted_class_idx] * 100
-        predicted_label = model.config.id2label[predicted_class_idx]
+        assessment = data["health_assessment"]
+        predicted_disease = assessment.get("diseases", [{}])[0].get("name", "Unknown Disease")
+        treatment = assessment.get("diseases", [{}])[0].get("treatment", "No treatment suggestions available.")
 
-        treatment = fetch_treatment_info(predicted_label)
+        return f"🌱 **Predicted Disease:** {predicted_disease}\n💊 **Treatment:** {treatment}"
 
-        return predicted_label, confidence.item(), treatment
     except Exception as e:
         logging.error(f"Prediction failed: {str(e)}")
-        return "Error", 0, "Error in prediction."
+        return f"❌ Error: {str(e)}"
 
-# Create a Gradio UI with Tabs & Styling
-with gr.Blocks(css="body {background-color: #f7f9fc;}") as app:
-    gr.Markdown(
-        "<h1 style='text-align: center;'>🌿 AI-Powered Plant Disease Detector</h1>",
-        elem_id="title"
-    )
-    
-    with gr.Tabs():
-        with gr.TabItem("📷 Detect Disease"):
-            with gr.Row():
-                image_input = gr.Image(type="numpy", label="📸 Upload a plant image", interactive=True)
-            
-            with gr.Row():
-                btn_predict = gr.Button("🔍 Analyze", variant="primary")
-            
-            with gr.Row():
-                disease_output = gr.Textbox(label="🌱 Disease", interactive=False)
-                confidence_output = gr.Slider(minimum=0, maximum=100, interactive=False, label="🔬 Confidence (%)")
-            
-            with gr.Row():
-                treatment_output = gr.Textbox(label="💊 Suggested Treatment", interactive=False)
-            
-            btn_predict.click(predict, inputs=[image_input], outputs=[disease_output, confidence_output, treatment_output])
-        
-        with gr.TabItem("📖 Prevention Guide"):
-            gr.Markdown("""
-                ## 🌾 How to Keep Your Plants Healthy?
-                - 🏡 Ensure Proper Spacing to Avoid Fungal Growth
-                - 💧 Water in the Morning to Reduce Disease Spread
-                - 🛑 Regularly Inspect & Remove Infected Leaves
-                - ☀️ Allow Good Sunlight & Ventilation for Stronger Plants
-                - 🍀 Use Organic Pesticides & Fungicides When Necessary
-            """)
-    
-app.launch()
+# Gradio Interface
+iface = gr.Interface(
+    fn=analyze_plant_health,
+    inputs=gr.Image(type="pil", label="📸 Upload or capture a plant image"),
+    outputs=gr.Textbox(label="🔍 Diagnosis & Treatment"),
+    title="🌿 AI-Powered Plant Disease Detector",
+    description="📷 Upload a leaf image to detect plant diseases and get treatment suggestions from Plant.id API.",
+    allow_flagging="never",
+    theme="default",
+)
+
+# Launch Gradio App
+if __name__ == "__main__":
+    iface.launch()