app.py

app.py

@@ -4,4 +4,30 @@ import numpy as np
 from sentence_transformers import SentenceTransformer
 import faiss
 import pickle
-import time
+import time
+
+# Загрузка данных
+@st.cache_data
+def load_data_models():
+    data = pd.read_csv('tvshows.csv')
+    # data['description'] = data['description'].astype(str)
+    description_embeddings = np.load('description_embeddings_mpnet.npy')
+    index = faiss.read_index('faiss_index.index')
+    embedder = SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')
+
+    return data, description_embeddings, index, embedder
+
+data, description_embeddings, index, embedder = load_data_models()
+
+def search_series(user_query, top_k=10):
+    query_embedding = embedder.encode([user_query], convert_to_tensor=True).cpu().numpy()
+    query_embedding = query_embedding / np.linalg.norm(query_embedding, axis=1, keepdims=True)  # Нормализация
+    D, I = index.search(query_embedding, top_k)
+    results = data.iloc[I[0]].copy()
+    cosine_similarities = D[0]
+    results['cosine_similarity'] = cosine_similarities
+    return results[['tvshow_title', 'description', 'cosine_similarity']]
+
+st.title('Поиск сериала по описанию')
+input_text = st.text_area('Введите описание сериала')
+st.write(search_series(input_text))

description_embeddings_mpnet.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2f2b4bc485f7af8480d06aec98f940350a5baeb02951825fa8d293248d719e
+size 147584

faiss_index.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cddf7aea0d3baddf96da3f9da3ac39aa0dc4b5ff1d2e8c5fb067c10d251446e
+size 147501