Update app.py

app.py

@@ -1,4 +1,3 @@
-
 import gradio as gr
 import matplotlib.pyplot as plt
 from PIL import Image
@@ -6,58 +5,85 @@ from ultralytics import YOLO
 import cv2
 import numpy as np
 import requests
-from io import BytesIO
+import json
 import os
 
 model = YOLO('Corn-Disease50Epoch.pt')
 name = ['Leaf Blight', 'Corn Rust', 'Gray Leaf Spot', 'Healthy']
 image_directory = "/home/user/app/images"
 
+def get_deepseek_solution(disease_name):
+    try:
+        response = requests.post(
+            url="https://openrouter.ai/api/v1/chat/completions",
+            headers={
+                "Authorization": f"Bearer {API_KEY}",
+                "Content-Type": "application/json"
+            },
+            data=json.dumps({
+                "model": "deepseek/deepseek-r1-distill-llama-70b:free",
+                "messages": [
+                    {
+                        "role": "system",
+                        "content": "Anda adalah asisten yang hanya dapat memberikan jawaban berdasarkan materi yang diberikan."
+                    },
+                    {
+                        "role": "user",
+                        "content": f"Apa penyebab dan solusi penyakit jagung '{disease_name}'?"
+                    }
+                ]
+            })
+        )
+
+        if response.status_code == 200:
+            result = response.json()
+            return result.get("choices", [{}])[0].get("message", {}).get("content", "").strip()
+        else:
+            return "DeepSeek gagal memberikan jawaban (kode error: {}).".format(response.status_code)
+
+    except requests.exceptions.RequestException as e:
+        return f"Gagal terhubung ke DeepSeek: {e}"
+
 def response2(image, image_size=640, conf_threshold=0.3, iou_threshold=0.6):
     results = model.predict(image, conf=conf_threshold, iou=iou_threshold, imgsz=image_size)
-                       
+    
     text = ""
-    name_weap = ""
     solution = ""
 
+    detected_diseases = set()
+
     for r in results:
         im_array = r.plot()
-        im = Image.fromarray(im_array[..., ::-1])
-
+        im = Image.fromarray(im_array[..., ::-1]) 
     for r in results:
         conf = np.array(r.boxes.conf.cpu())
-        cls = np.array(r.boxes.cls.cpu())
-        cls = cls.astype(int)
-        xywh = np.array(r.boxes.xywh.cpu())
-        xywh = xywh.astype(int)  
-      
+        cls = np.array(r.boxes.cls.cpu()).astype(int)
+        xywh = np.array(r.boxes.xywh.cpu()).astype(int)
+
         for con, cl, xy in zip(conf, cls, xywh):
-            cone = con.astype(float)
-            conef = round(cone, 3)
-            conef = conef * 100
-            text += (f"Detected {name[cl]} with confidence {round(conef, 1)}% at ({xy[0]},{xy[1]})\n")
-                
-            if name[cl] == "Corn Rust":
-                solution = (f"{solution} Apply fungicides with active ingredients like propiconazole or tebuconazole when symptoms appear.\n") 
-            elif name[cl] == "Gray Leaf Spot":
-                solution = (f"{solution} Use fungicides containing strobilurins (e.g., azoxystrobin) or triazoles.\n") 
-            elif name[cl] == "Leaf Blight":
-                solution = (f"{solution} Treat with fungicides such as mancozeb or chlorothalonil during the early stages.\n") 
-           
-    return im, text, solution
+            confidence = round(float(con) * 100, 1)
+            text += f"Detected {name[cl]} with confidence {confidence}% at ({xy[0]},{xy[1]})\n"
+            detected_diseases.add(name[cl])
+
+    for disease in detected_diseases:
+        if disease != "Healthy":
+            solution += f"\n--- {disease} ---\n"
+            deepseek_explanation = get_deepseek_solution(disease)
+            solution += deepseek_explanation + "\n"
+        else:
+            solution += "\nTanaman tampak sehat. Tidak ada tindakan diperlukan.\n"
+
+    return im, text.strip(), solution.strip()
 
 def pil_to_cv2(pil_image):
-    open_cv_image = cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
-    return open_cv_image
+    return cv2.cvtColor(np.array(pil_image), cv2.COLOR_RGB2BGR)
 
 def process_video(video_path):
     cap = cv2.VideoCapture(video_path)
-    
     while cap.isOpened():
         ret, frame = cap.read()
         if not ret:
             break
-        
         pil_img = Image.fromarray(frame[..., ::-1])  
         result = model.predict(source=pil_img)
         for r in result:
@@ -76,7 +102,7 @@ inputs = [
 outputs = [
     gr.Image(type="pil", label="Output Image"),
     gr.Textbox(label="Result"), 
-    gr.Textbox(label="Solution")
+    gr.Textbox(label="AI-Powered Solution")
 ]
 
 examples = [
@@ -108,4 +134,5 @@ image_iface = gr.Interface(
 demo = gr.TabbedInterface([image_iface, video_iface], ["Image Inference", "Video Inference"])
 
 if __name__ == '__main__':
-    demo.launch()
+    demo.launch()
+