|
--- |
|
title: Nn Ext |
|
emoji: π¦ |
|
colorFrom: blue |
|
colorTo: purple |
|
sdk: streamlit |
|
sdk_version: 1.31.0 |
|
app_file: app.py |
|
pinned: false |
|
--- |
|
# Streamlit app with neural network π‘ |
|
|
|
## Teamπ§π»βπ» |
|
1. [Diachenko Ilia](https://github.com/DiaElijah) |
|
2. [Yerlan Baidildin](https://github.com/YerlanBaidildin) |
|
|
|
## Task π |
|
1. Parse a movie database online. |
|
2. Creating a service for semantic movie search using pre-trained language models. |
|
|
|
## Contents π€ |
|
1. Data parsing was carried out from the site π½οΈ [kino.mail.ru](https://kino.mail.ru/cinema/all/) |
|
2. Models used for semantic search π€ [rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2) and π [msmarco-MiniLM-L-12-v3](https://www.sbert.net/docs/pretrained-models/msmarco-v3.html) |
|
3. The library was used for semantic search πΎ [Sentence Transformers](https://www.sbert.net/examples/applications/semantic-search/README.html#) |
|
|
|
## Libraries π |
|
```python |
|
import json |
|
import requests |
|
from bs4 import BeautifulSoup |
|
import pandas as pd |
|
import time |
|
import csv |
|
import re |
|
import ast |
|
import re |
|
import string |
|
import nltk |
|
import pymorphy2 |
|
import streamlit as st |
|
import numpy as np |
|
import torch |
|
from sentence_transformers import SentenceTransformer, util |
|
``` |