Spaces:
Runtime error
Runtime error
Update stri.py
Browse files
stri.py
CHANGED
@@ -2,6 +2,7 @@ import streamlit as st
|
|
2 |
import torch
|
3 |
import numpy as np
|
4 |
import pandas as pd
|
|
|
5 |
from transformers import AutoTokenizer, AutoModel
|
6 |
import re
|
7 |
import pickle
|
@@ -17,7 +18,6 @@ model = AutoModel.from_pretrained(model_name, output_hidden_states=True)
|
|
17 |
books = pd.read_csv('books_6000.csv')
|
18 |
books.dropna(inplace=True)
|
19 |
|
20 |
-
|
21 |
books = books[books['annotation'].apply(lambda x: len(x.split()) >= 10)]
|
22 |
books.drop_duplicates(subset='title', keep='first', inplace=True)
|
23 |
books = books.reset_index(drop=True)
|
@@ -42,24 +42,24 @@ max_len = 128
|
|
42 |
# Определение запроса пользователя
|
43 |
query = st.text_input("Введите запрос")
|
44 |
|
45 |
-
if st.button('
|
46 |
with open("book_embeddings.pkl", "rb") as f:
|
47 |
book_embeddings = pickle.load(f)
|
48 |
-
|
49 |
query_tokens = tokenizer.encode(query, add_special_tokens=True,
|
50 |
truncation=True, max_length=max_len)
|
51 |
-
|
52 |
query_padded = np.array(query_tokens + [0] * (max_len - len(query_tokens)))
|
53 |
query_mask = np.where(query_padded != 0, 1, 0)
|
54 |
-
|
55 |
# Переведем numpy массивы в тензоры PyTorch
|
56 |
query_padded = torch.tensor(query_padded, dtype=torch.long)
|
57 |
query_mask = torch.tensor(query_mask, dtype=torch.long)
|
58 |
-
|
59 |
with torch.no_grad():
|
60 |
query_embedding = model(query_padded.unsqueeze(0), query_mask.unsqueeze(0))
|
61 |
-
query_embedding = query_embedding[0][:, 0, :]
|
62 |
-
|
63 |
# Вычисление косинусного расстояния между эмбеддингом запроса и каждой аннотацией
|
64 |
cosine_similarities = torch.nn.functional.cosine_similarity(
|
65 |
query_embedding.squeeze(0),
|
@@ -67,8 +67,14 @@ if st.button('**Generating recommendations**'):
|
|
67 |
)
|
68 |
|
69 |
cosine_similarities = cosine_similarities.numpy()
|
70 |
-
|
71 |
indices = np.argsort(cosine_similarities)[::-1] # Сортировка по убыванию
|
72 |
-
|
73 |
-
|
74 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
import torch
|
3 |
import numpy as np
|
4 |
import pandas as pd
|
5 |
+
from PIL import Image
|
6 |
from transformers import AutoTokenizer, AutoModel
|
7 |
import re
|
8 |
import pickle
|
|
|
18 |
books = pd.read_csv('books_6000.csv')
|
19 |
books.dropna(inplace=True)
|
20 |
|
|
|
21 |
books = books[books['annotation'].apply(lambda x: len(x.split()) >= 10)]
|
22 |
books.drop_duplicates(subset='title', keep='first', inplace=True)
|
23 |
books = books.reset_index(drop=True)
|
|
|
42 |
# Определение запроса пользователя
|
43 |
query = st.text_input("Введите запрос")
|
44 |
|
45 |
+
if st.button('Сгенерировать'):
|
46 |
with open("book_embeddings.pkl", "rb") as f:
|
47 |
book_embeddings = pickle.load(f)
|
48 |
+
|
49 |
query_tokens = tokenizer.encode(query, add_special_tokens=True,
|
50 |
truncation=True, max_length=max_len)
|
51 |
+
|
52 |
query_padded = np.array(query_tokens + [0] * (max_len - len(query_tokens)))
|
53 |
query_mask = np.where(query_padded != 0, 1, 0)
|
54 |
+
|
55 |
# Переведем numpy массивы в тензоры PyTorch
|
56 |
query_padded = torch.tensor(query_padded, dtype=torch.long)
|
57 |
query_mask = torch.tensor(query_mask, dtype=torch.long)
|
58 |
+
|
59 |
with torch.no_grad():
|
60 |
query_embedding = model(query_padded.unsqueeze(0), query_mask.unsqueeze(0))
|
61 |
+
query_embedding = query_embedding[0][:, 0, :]
|
62 |
+
|
63 |
# Вычисление косинусного расстояния между эмбеддингом запроса и каждой аннотацией
|
64 |
cosine_similarities = torch.nn.functional.cosine_similarity(
|
65 |
query_embedding.squeeze(0),
|
|
|
67 |
)
|
68 |
|
69 |
cosine_similarities = cosine_similarities.numpy()
|
70 |
+
|
71 |
indices = np.argsort(cosine_similarities)[::-1] # Сортировка по убыванию
|
72 |
+
|
73 |
+
num_books_per_page = st.selectbox("Количество книг на странице:", [3, 5, 10], index=0)
|
74 |
+
|
75 |
+
for i in indices[:num_books_per_page]:
|
76 |
+
st.write("## " + books['title'][i])
|
77 |
+
st.write("**Автор:**", books['author'][i])
|
78 |
+
st.write("**Аннотация:**", books['annotation'][i])
|
79 |
+
st.image(Image.open(books['image_url'][i]))
|
80 |
+
st.write("---")
|