Upload 3 files

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 pages/MiniLM/MiniLM_index.index filter=lfs diff=lfs merge=lfs -text
 mpnet_base/mpnet_base_index.index filter=lfs diff=lfs merge=lfs -text
+pages/mpnet_base/mpnet_base_index.index filter=lfs diff=lfs merge=lfs -text

pages/mpnet_base/mpnet_base_app.py

@@ -0,0 +1,129 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sentence_transformers import SentenceTransformer
+import faiss
+import pickle
+import time
+
+# Загрузка данных
+@st.cache_data
+def load_data_models():
+    data = pd.read_csv('data/books_data2.csv')
+    data['annotation'] = data['annotation'].astype(str)
+    with open('pages/mpnet_base/mpnet_base_embeddings.pkl', 'rb') as f:
+        book_embeddings = pickle.load(f)
+
+    index = faiss.read_index('pages/mpnet_base/mpnet_base_index.index')
+    embedder = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
+
+    return data, book_embeddings, index, embedder
+
+data, book_embeddings, index, embedder = load_data_models()
+
+# Функция для поиска
+def search_books(query, num_results):
+    query_embedding = embedder.encode([query], convert_to_tensor=True)
+    query_embedding_cpu = query_embedding.cpu()
+    query_embedding_normalized = query_embedding_cpu / np.linalg.norm(query_embedding_cpu, axis=1)
+    D, I = index.search(np.array(query_embedding_normalized), num_results)
+    return I[0], D[0] 
+
+# Streamlit
+def mpnet_base_page():
+    st.title('Поиск книг')
+    user_input = st.text_input("Введите цитату или автора:")
+    results_num = st.slider("Количество результатов", min_value=1, max_value=20, value=5)
+
+    if st.button('Искать'):
+        start_time = time.time() 
+        indices, distances = search_books(user_input, results_num)
+        end_time = time.time()  
+        search_time = end_time - start_time
+        st.write("Результаты поиска:")
+        for idx, dist in zip(indices, distances):
+            book = data.iloc[idx]
+            st.write("---")
+            st.image(book['image_url'], width=250)
+            st.write(f"**Название:** {book['title']}")
+            st.write(f"**Автор:** {book['author']}")
+            st.write(f"**Жанр:** {book['genre']}")
+            if len(book['annotation']) > 50:
+                book['annotation'] = ' '.join(book['annotation'].split()[:50]) + '...'
+            st.write(f"**Описание:** {book['annotation']}")
+            st.write(f"**Метрика близости:** {dist}")
+            st.write(f'**Время поиска:** {search_time:.4f} секунд')
+            st.markdown(f"[Читать подробнее]({book['page_url']})", unsafe_allow_html=True)
+
+
+
+
+
+# # Загрузка данных
+# @st.cache_data
+# def load_data():
+#     data = pd.read_csv('Data/books_data2.csv')
+#     with open('pages/MiniLM/MiniLM_embeddings.pkl', 'rb') as f:
+#         book_embeddings = pickle.load(f)
+#     index = faiss.read_index('pages/MiniLM/MiniLM_index.index')
+
+#     embedder = SentenceTransformer("all-MiniLM-L6-v2")
+#     return data, index, embedder
+
+# # Функция поиска
+# def search_books(embedder, index, data, query, n_results):
+#     query_embedding = embedder.encode([query])
+#     D, I = index.search(query_embedding, n_results)
+    
+#     result_books = []
+#     for i in range(n_results):
+#         book_index = I[0][i]
+#         book_info = data.iloc[book_index]
+#         book_link = book_info['page_url']
+#         book_image = book_info['image_url']
+#         book_genre = book_info['genre']
+#         book_title = book_info['title']
+#         book_description = book_info['annotation']
+#         book_author = book_info['author']
+#         similarity_score = 1 / (1 + D[0][i])
+        
+#         result_books.append({
+#             'Link': book_link,
+#             'Image': book_image,
+#             'Genre': book_genre,
+#             'Title': book_title,
+#             'Description': book_description,
+#             'Author': book_author,
+#             'Similarity': similarity_score
+#         })
+    
+#     return result_books
+
+# # Streamlit
+# def MiniLm_page():
+#     st.title('Поиск книг')
+#     data, index, embedder = load_data()
+#     query = st.text_input('Введите цитату или автора:')
+#     n_results = st.slider("Количество результатов", min_value=1, max_value=20, value=5)
+
+#     if st.button("Искать"):
+#         if query:
+#             start_time = time.time() 
+#             result_books = search_books(embedder, index, data, query, n_results)
+#             end_time = time.time()  
+#             search_time = end_time - start_time 
+#             st.write("Результаты поиска:")
+            
+#             for book in result_books:
+#                 st.write('---')
+#                 st.image(book['Image'], width=250)
+#                 st.write(f"**Название:** {book['Title']}")
+#                 st.write(f"**Автор:** {book['Author']}")
+#                 st.write(f"**Жанр:** {book['Genre']}")
+#                 if len(book['Description']) > 50:
+#                     book['Description'] = ' '.join(book['Description'].split()[:50]) + '...'
+#                 st.write(f"**Описание:** {book['Description']}")
+#                 st.write(f"**Сходство:** {book['Similarity']:.2f}")
+#                 st.write(f'**Время поиска:** {search_time:.4f} секунд')
+#                 st.write(f"[Читать подробнее]({book['Link']})")
+#                 st.text("") 

pages/mpnet_base/mpnet_base_embeddings.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a32d3e04e31c06f6b3162818e62c9b353e9301648097c607ecc5090021f5a8d
+size 15157411

pages/mpnet_base/mpnet_base_index.index

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27842f132ba09b2ff5908ce74c12e4ad89c3a7e01e056f84ef687697fef0f72
+size 15157293