step 6

app.py

@@ -24,12 +24,6 @@ def preprocess_image(image):
     ])
     return preprocess(pil_image).unsqueeze(0)
 
-def generate_output_html(top_3_products):
-    output_html = ""
-    for i, product in enumerate(top_3_products):
-        output_html += f'<div class="product"><img src="{product["image_url"]}" alt="{product["name"]}" /><br>{product["name"]}<br>Price: {product["price"]}</div>'
-    return output_html
-
 def encode_text(text):
     inputs = processor(text=[text], return_tensors="pt", padding=True, truncation=True)
     return inputs
@@ -38,6 +32,34 @@ def encode_image(image):
     inputs = processor(images=[image], return_tensors="pt", padding=True, truncation=True)
     return inputs
 
+def calculate_similarities(query_image, query_text):
+    query_image_features = model.get_image_features(query_image)
+    query_text_features = model.get_text_features(query_text)
+
+    similarities = []
+    for product in deepfashion_database:
+        product_image_features = torch.Tensor(product["image_features"])
+        product_text_features = torch.Tensor(product["text_features"])
+
+        image_similarity = torch.nn.CosineSimilarity(dim=-1)(query_image_features, product_image_features)
+        text_similarity = torch.nn.CosineSimilarity(dim=-1)(query_text_features, product_text_features)
+        
+        similarity_score = image_similarity * text_similarity
+        similarities.append(similarity_score)
+
+    return similarities
+
+def initial_query(image, text):
+    query_image = encode_image(image)
+    query_text = encode_text(text)
+
+    similarities = calculate_similarities(query_image, query_text)
+    sorted_indices = sorted(range(len(similarities)), key=lambda i: similarities[i], reverse=True)
+    top_3_indices = sorted_indices[:3]
+
+    top_3_products = [deepfashion_database[i] for i in top_3_indices]
+    return top_3_products
+
 def send_message(txt, btn):
     if btn is not None:
         image = preprocess_image(btn)