Upload 4 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data_final.csv filter=lfs diff=lfs merge=lfs -text
+vectors.txt filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,48 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import torch
+from transformers import AutoTokenizer, AutoModel
+from sklearn.metrics.pairwise import pairwise_distances, cosine_similarity
+
+tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny2")
+model = AutoModel.from_pretrained("cointegrated/rubert-tiny2")
+
+df = pd.read_csv('data_final.csv')
+
+MAX_LEN = 300
+
+# @st.cache_resource
+def embed_bert_cls(text, model, tokenizer):
+    t = tokenizer(text, padding=True, truncation=True, return_tensors='pt', max_length=MAX_LEN)
+    with torch.no_grad():
+        model_output = model(**{k: v.to(model.device) for k, v in t.items()})
+    embeddings = model_output.last_hidden_state[:, 0, :]
+    embeddings = torch.nn.functional.normalize(embeddings)
+    return embeddings[0].cpu().numpy()
+
+books_vector = np.loadtxt('vectors.txt')
+
+st.title('Приложение для рекомендации книг')
+
+text = st.text_input('Введите запрос:')
+num_results = st.number_input('Введите количество рекомендаций:', min_value=1, max_value=50, value=1)
+
+recommend_button = st.button('Найти')
+
+if text and recommend_button:
+    user_text_pred = embed_bert_cls(text, model, tokenizer)
+    list_ = pairwise_distances(user_text_pred.reshape(1, -1), books_vector).argsort()[0][:num_results]
+
+    st.subheader('Топ рекомендуемых книг:')
+
+    for i in list_:
+        col_1, col_2 = st.columns([1, 3])
+
+        with col_1:
+            st.image(df['image_url'][i], use_column_width=True)
+        with col_2:
+            st.write(f'Название книги: {df["title"][i]}')
+            st.write(f'Название книги: {df["author"][i]}')
+            st.write(f'Название книги: {df["annotation"][i]}')
+            st.write(f'{df["page_url"][i]}')

data_final.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0134e0f425d7cde2b5a1c063b600f91a19e0a402305bdd836d7c4c6f62063ee
+size 13156346

requirements.txt

@@ -0,0 +1 @@
+torch==2.0.1

vectors.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd2885b9809cf7b6fd597bdd76d1d38d7a96ef1273fac87a418881c6afbf836
+size 32849065