new app.py

app.py

@@ -7,7 +7,7 @@ import string
 import re
 import joblib
 # import pickle
-# import time
+import time
 
 # st.markdown("""
 #     <style>
@@ -84,7 +84,7 @@ def clean_text(text):
     text = text.lower()
     return text
 
-def search_series(user_query, top_k=10):
+def search_series(user_query, top_k):
     user_query = clean_text(user_query)
     query_embedding = embedder.encode([user_query], convert_to_tensor=True).cpu().numpy()
     weighted_query_embedding = np.concatenate((query_embedding * description_weight,
@@ -93,12 +93,31 @@ def search_series(user_query, top_k=10):
     weighted_query_embedding = lsa.transform(weighted_query_embedding)
     weighted_query_embedding = weighted_query_embedding / np.linalg.norm(weighted_query_embedding, axis=1, keepdims=True)  # Нормализация
     D, I = index.search(weighted_query_embedding, top_k)
-    results = data.iloc[I[0]].copy()
-    cosine_similarities = D[0]
-    results['cosine_similarity'] = cosine_similarities
-    return results
+    # results = data.iloc[I[0]].copy()
+    # cosine_similarities = D[0]
+    # results['cosine_similarity'] = cosine_similarities
+    return I[0], D[0] 
+
+
 
 st.title('Поиск сериала по описанию')
 input_text = st.text_area('Введите описание сериала')
+top_k = st.slider("Количество результатов", min_value=1, max_value=20, value=5)
 if st.button('Поиск'):
-    st.write(search_series(input_text))
+        start_time = time.time() 
+        indices, distances = search_series(input_text, top_k)
+        end_time = time.time()  
+        search_time = end_time - start_time
+        st.write("Результаты поиска:")
+        for idx, dist in zip(indices, distances):
+            results = data.iloc[idx]
+            st.write("---")
+            st.image(results['image_url'], width=250)
+            st.write(f"**Название:** {results['tvshow_title']}")
+            st.write(f"**Жанр:** {results['genre']}")
+            if len(results['description']) > 50:
+                results['description'] = ' '.join(results['description'].split()[:50]) + '...'
+            st.write(f"**Описание:** {results['description']}")
+            st.write(f"**Косинусное сходство:** {dist}")
+            st.write(f'**Время поиска:** {search_time:.4f} секунд')
+            st.markdown(f"[Читать далее]({results['page_url']})", unsafe_allow_html=True)