Update app.py

app.py

@@ -13,29 +13,29 @@ def load_data(url):
 
 df = load_data('data/final_data.csv')
 
-@st.cache_data
-def embedding_and_index():
-    embeddings_array = np.load('data/embeddings_final.npy')
-    index = faiss.read_index('data/desc_faiss_index_final.index')
-    return(embeddings_array, index)
+# @st.cache_data
+# def embedding_and_index():
+#     embeddings_array = np.load('data/embeddings_final.npy')
+#     index = faiss.read_index('data/desc_faiss_index_final.index')
+#     return(embeddings_array, index)
 
-embeddings_array, index = embedding_and_index()
+# embeddings_array, index = embedding_and_index()
      
-@st.cache_resource
-def load_tokenizer_and_model():
-    tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/rubert-base-cased-sentence")
-    model = AutoModel.from_pretrained("DeepPavlov/rubert-base-cased-sentence")
-    return tokenizer, model
+# @st.cache_resource
+# def load_tokenizer_and_model():
+#     tokenizer = AutoTokenizer.from_pretrained("DeepPavlov/rubert-base-cased-sentence")
+#     model = AutoModel.from_pretrained("DeepPavlov/rubert-base-cased-sentence")
+#     return tokenizer, model
     
-tokenizer, model = load_tokenizer_and_model()
-
-@st.cache_resource
-def encode_description(description, tokenizer, model):
-    tokens = tokenizer(description, return_tensors="pt")
-    with torch.no_grad():
-        outputs = model(**tokens)
-    embeddings = outputs.last_hidden_state.mean(dim=1)
-    return embeddings.cpu().numpy().astype('float32')
+# tokenizer, model = load_tokenizer_and_model()
+
+# @st.cache_resource
+# def encode_description(description, tokenizer, model):
+#     tokens = tokenizer(description, return_tensors="pt")
+#     with torch.no_grad():
+#         outputs = model(**tokens)
+#     embeddings = outputs.last_hidden_state.mean(dim=1)
+#     return embeddings.cpu().numpy().astype('float32')
 
 
 st.title('Умный поиск фильмов 🔍🎦')