feat: change response format to JSON

app.py

@@ -22,14 +22,17 @@ def predict(image):
         api_name="/predict"
     )
     
-    label , confidence = imgResult[0]['label'] , float(imgResult[1]['label'])
+    label , confidence = imgResult[0]['label'] , float(imgResult[1]['label'])    
 
-    if label == 'finger_gun_to_the_head' and confidence > 0.98:
-        return ["hate" , f"label: {label}, confidence: {confidence}"]
-    elif label != 'finger_gun_to_the_head' and confidence > 0.95:
-        return ["hate" , f"label: {label}, confidence: {confidence}"]
+    if (label == 'finger_gun_to_the_head' and confidence > 0.98) or (label != 'finger_gun_to_the_head' and confidence > 0.95):
+        return {
+            "prediction" : "hate",
+            "language" : None,
+            "label" : label,
+            "confidence" : confidence,
+            "hate_text" : None
+        }
     else:
- 
         ocr_text = extract_text(image).lower()
         
         engResult = clientEngText.predict(
@@ -42,25 +45,47 @@ def predict(image):
         		api_name="/predict"
         )
 
-        profanityFound = any(word in ocr_text.split() for word in profanity_hn)
+        profanityFound = [word for word in profanity_hn if word in ocr_text[:200].split()]
+
+        if len(profanityFound) > 0:
+            return {
+                "prediction" : "hate",
+                "language" : "Hindi",
+                "label" : "Profanity Found",
+                "confidence" : None,
+                "hate_text" : profanityFound
+            }
 
-        if profanityFound:
-            return ["hate", "Profanity Found"]
         elif engResult[0] != "NEITHER" and engResult[1] > 0.5:
-            return ["hate", f"Result: {engResult}, Text: {ocr_text}"]
+            return {
+                "prediction" : "hate",
+                "language" : "English",
+                "label" : engResult[0],
+                "confidence" : engResult[1],
+                "hate_text" : ocr_text[:200]
+            }
+
         elif hingResult[0] != "NAG" and hingResult[1] > 0.5:
-            return ["hate", f"Result: {hingResult}, Text: {ocr_text}"]
+            return {
+                "prediction" : "hate",
+                "language" : "Hinglish",
+                "label" : hingResult[0],
+                "confidence" : hingResult[1],
+                "hate_text" : ocr_text[:200]
+            }
+
         else:
-            return ["not_hate", "No hate found, yay!"]
-        
-        # if not profanityFound and engResult[0] == "NEITHER" and hingResult[0] == "NAG":
-        #     return ["not_hate" , "No Hate Symbols Detected"]
-        # else:
-        #     return ["hate" , "No Hate Symbols Detected"]
+            return {
+                "prediction" : "not_hate",
+                "language" : None,
+                "label" : "No hate found, yay!",
+                "confidence" : None,
+                "hate_text" : None
+            }
         
 iface = gr.Interface(fn=predict,
                      inputs = gr.Image(type='filepath'),
-                     outputs=[gr.Label(label = "Class (hate or not_hate)") , gr.Label(label = "Explanation")],
+                     outputs=gr.JSON(),         
                      title = "Hate Speech Detection in Image",
                      description = "Detect hateful symbols or text in Image"
         )