Update app.py

app.py

@@ -1,74 +1,19 @@
 import gradio as gr
-from transformers import pipeline
-from PIL import Image
+from crop_disease_monitor.inference.inference import load_disease_pipeline, diagnose
 
-# Initialize two classification pipelines with authentication
-plant_disease_classifier = pipeline(
-    task="image-classification",  
-    model="linkanjarad/mobilenet_v2_1.0_224-plant-disease-identification",
-    top_k=3
-)
-nutrient_deficiency_classifier = pipeline(
-    task="image-classification",
-    model="nateraw/vit-base-beans",
-    top_k=3
-)
-
-def diagnose_crop_health(image: Image.Image):
-    """
-    Takes a PIL Image of a crop leaf and returns:
-      - Top 3 disease predictions
-      - Top 3 nutrient deficiency predictions
-      - Combined care advice based on both
-    """
-    disease_results = plant_disease_classifier(image)
-    nutrient_results = nutrient_deficiency_classifier(image)
-
-    disease_preds = [f"{res['label']} ({res['score']*100:.1f}%)" for res in disease_results]
-    nutrient_preds = [f"{res['label']} ({res['score']*100:.1f}%)" for res in nutrient_results]
-
-    # Generate advice based on predictions
-    advices = []
-    top_disease = disease_results[0]['label'].lower()
-    top_nutrient = nutrient_results[0]['label'].lower()
+# load your published model or local checkpoint
+pipe = load_disease_pipeline("CZerion/COMP-019_Assignment-Crop_Health_Monitor")
 
-    if "healthy" in top_disease:
-        advices.append("No disease detected—maintain standard crop care.")
-    else:
-        advices.append(f"Disease detected: {disease_results[0]['label']}. Isolate and apply targeted treatment.")
-
-    if "healthy" in top_nutrient:
-        advices.append("No nutrient deficiency detected—continue regular fertilization.")
-    else:
-        advices.append(f"Nutrient issue: {nutrient_results[0]['label']}. Amend soil based on deficiency (e.g., add N, P, or K).")
-
-    return "\n".join(disease_preds), "\n".join(nutrient_preds), "\n".join(advices)
-
-# Build the Gradio interface
 iface = gr.Interface(
-    fn=diagnose_crop_health,
-    inputs=gr.Image(type="pil", label="Upload Crop Leaf Image"),
+    fn=lambda img: diagnose(img, pipe),
+    inputs=gr.Image(type="pil", label="Upload Leaf Image"),
     outputs=[
         gr.Textbox(label="Disease Predictions (Top 3)"),
-        gr.Textbox(label="Nutrient Predictions (Top 3)"),
         gr.Textbox(label="Care Advice")
     ],
-    title="Crop Health Monitor",
-    description=(
-        "Upload a photo of your crop's leaf to diagnose diseases and nutrient deficiencies, "
-        "and receive combined care recommendations using two complementary models."
-    ),
-    examples=[
-        ["Plants/Unhealthy_crop_1.jpg"],
-        ["Plants/Unhealthy_crop_2.jpg"],
-        ["Plants/Unhealthy_crop_3.jpg"],
-        ["Plants/Unhealthy_crop_4.jpg"],
-        ["Plants/Unhealthy_crop_5.jpg"],
-        ["Plants/Healthy_crop_1.jpg"],
-        ["Plants/Healthy_crop_2.jpg"]
-    ],
-    allow_flagging="never"
+    title="Plant Disease Monitor",
+    description="Upload a crop leaf photo to detect diseases using a fine-tuned model."
 )
 
 if __name__ == "__main__":
-    iface.launch(server_name="0.0.0.0", server_port=7860)
+    iface.launch()