Update pipeline/routes.py

pipeline/routes.py

@@ -6,20 +6,17 @@ from flask import request, jsonify
 # Import app, models, and logic functions
 from pipeline import app, models, logic
 
-
 @app.route('/process', methods=['POST'])
 def process_item():
-    print("\n" + "=" * 50)
+    print("\n" + "="*50)
     print("➡ [Request] Received new request to /process")
-
     try:
         data = request.get_json()
-        if not data:
-            return jsonify({"error": "Invalid JSON payload"}), 400
+        if not data: return jsonify({"error": "Invalid JSON payload"}), 400
 
         object_name = data.get('objectName')
         description = data.get('objectDescription')
-        image_url = data.get('objectImage')
+        image_url = data.get('objectImage') 
 
         if not all([object_name, description]):
             return jsonify({"error": "objectName and objectDescription are required."}), 400
@@ -42,7 +39,7 @@ def process_item():
             print("--- No image URL provided, skipping visual feature extraction. ---")
 
         print("✅ Successfully processed item.")
-        print("=" * 50)
+        print("="*50)
         return jsonify(response_data), 200
 
     except Exception as e:
@@ -50,23 +47,20 @@ def process_item():
         traceback.print_exc()
         return jsonify({"error": str(e)}), 500
 
-
 @app.route('/compare', methods=['POST'])
 def compare_items():
-    print("\n" + "=" * 50)
+    print("\n" + "="*50)
     print("➡ [Request] Received new request to /compare")
-
     try:
         data = request.get_json()
-        if not data:
-            return jsonify({"error": "Invalid JSON payload"}), 400
+        if not data: return jsonify({"error": "Invalid JSON payload"}), 400
 
         query_item = data.get('queryItem')
         search_list = data.get('searchList')
 
         if not all([query_item, search_list]):
             return jsonify({"error": "queryItem and searchList are required."}), 400
-
+        
         query_text_emb = np.array(query_item['text_embedding'])
         results = []
         print(f"--- Comparing 1 query item against {len(search_list)} items ---")
@@ -74,7 +68,6 @@ def compare_items():
         for item in search_list:
             item_id = item.get('_id')
             print(f"\n [Checking] Item ID: {item_id}")
-
             try:
                 text_emb_found = np.array(item['text_embedding'])
                 text_score = logic.cosine_similarity(query_text_emb, text_emb_found)
@@ -85,27 +78,20 @@ def compare_items():
 
                 if has_query_image and has_item_image:
                     print(" - Both items have images. Performing visual comparison.")
-                    from pipeline import FEATURE_WEIGHTS  # Import constant
-
+                    from pipeline import FEATURE_WEIGHTS # Import constant
                     query_shape = np.array(query_item['shape_features'])
                     query_color = np.array(query_item['color_features']).astype("float32")
                     query_texture = np.array(query_item['texture_features']).astype("float32")
-
                     found_shape = np.array(item['shape_features'])
                     found_color = np.array(item['color_features']).astype("float32")
                     found_texture = np.array(item['texture_features']).astype("float32")
-
                     shape_dist = cv2.matchShapes(query_shape, found_shape, cv2.CONTOURS_MATCH_I1, 0.0)
                     shape_score = 1.0 / (1.0 + shape_dist)
                     color_score = cv2.compareHist(query_color, found_color, cv2.HISTCMP_CORREL)
                     texture_score = cv2.compareHist(query_texture, found_texture, cv2.HISTCMP_CORREL)
-
-                    raw_image_score = (
-                        FEATURE_WEIGHTS["shape"] * shape_score +
-                        FEATURE_WEIGHTS["color"] * color_score +
-                        FEATURE_WEIGHTS["texture"] * texture_score
-                    )
-
+                    raw_image_score = (FEATURE_WEIGHTS["shape"] * shape_score +
+                                       FEATURE_WEIGHTS["color"] * color_score +
+                                       FEATURE_WEIGHTS["texture"] * texture_score)
                     print(f"Raw Image Score: {raw_image_score:.4f}")
                     image_score = logic.stretch_image_score(raw_image_score)
                     final_score = 0.4 * image_score + 0.6 * text_score
@@ -114,7 +100,7 @@ def compare_items():
                     print(" - One or both items missing image. Using text score only.")
                     final_score = text_score
 
-                from pipeline import FINAL_SCORE_THRESHOLD  # Import constant
+                from pipeline import FINAL_SCORE_THRESHOLD # Import constant
                 if final_score >= FINAL_SCORE_THRESHOLD:
                     print(f" - ✅ ACCEPTED (Score >= {FINAL_SCORE_THRESHOLD})")
                     results.append({
@@ -126,17 +112,16 @@ def compare_items():
                     })
                 else:
                     print(f" - ❌ REJECTED (Score < {FINAL_SCORE_THRESHOLD})")
-
             except Exception as e:
                 print(f" [Skipping] Item {item_id} due to processing error: {e}")
                 continue
 
         results.sort(key=lambda x: x["score"], reverse=True)
         print(f"\n✅ Search complete. Found {len(results)} potential matches.")
-        print("=" * 50)
+        print("="*50)
         return jsonify({"matches": results}), 200
 
     except Exception as e:
         print(f"❌ Error in /compare: {e}")
         traceback.print_exc()
-        return jsonify({"error": str(e)}), 500
+        return jsonify({"error": str(e)}), 500