update syntax connection

clip_component.py

@@ -6,7 +6,7 @@ import clip
 
 similarity_threshold = 22.00
 def get_token_from_clip(image):
-    text_inputs = ["apple", "banana", "lemon", "orange", "cereal", "salad", "chicken", "juice", "milk", "bread"]
+    text_inputs = ["apple", "banana", "cereal", "milk", "lemon", "orange",  "salad", "juice", "chicken", "bread"]
     text_tokens = clip.tokenize(text_inputs)
 
     device = "cpu"
@@ -28,18 +28,22 @@ def get_token_from_clip(image):
         similarity = text_features.cpu().numpy() @ image_feature.cpu().numpy().T
 
     results = []
-    detect_food = ""
+
 
     for i in range(similarity.shape[0]):
         similarity_num = (100.0 * similarity[i][0])
         text_input = text_inputs[i]
         results.append({"text_input": text_input, "similarity": similarity_num})
-        if similarity_num >= similarity_threshold:
-            detect_food += " " + text_input + " ."
         # print(similarity_num)
-    detect_food_list = detect_food[1:]
+
     results.sort(key=lambda x: x["similarity"], reverse=True)
     # Print the caption for each text input along with their similarity scores
+
+    detect_food = ""
     for result in results:
         print(f"Text input: {result['text_input']}, Similarity: {result['similarity']:.2f}")
+        if result['similarity'] >= similarity_threshold:
+            detect_food += " " + text_input + " ."
+
+    detect_food_list = detect_food[1:]
     return detect_food_list