Spaces:
Running
Running
File size: 7,739 Bytes
088848a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
import streamlit as st
import requests
from bs4 import BeautifulSoup
import re
from cleantext import clean
import streamlit.components.v1 as component
from transformers import pipeline
from functions import Copy_Text
from functions import *
### import animation
def particle(Js_file):
with open(Js_file) as f:
component.html(f"{f.read()}", height=400)
### insert external css
def insert_css(css_file:str):
with open(css_file) as f:
st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
# page settings
st.set_page_config(
layout="wide",
initial_sidebar_state="collapsed"
)
# sidebar
app_sidebar = st.sidebar
with app_sidebar:
select_mode = st.selectbox(
label="Select Mode",
options=["Summarizer","Que/Ans"],
key="mode selector",
index=0
)
if select_mode == "Que/Ans":
st.write("### Que/Ans Settings")
max_answer_length = st.slider(
label="Max answer",
min_value=1,
max_value=10,
key="max answer",
value=4
)
max_answer_length = max_answer_length*10
Best_size = st.slider(
label="n best size",
min_value=1,
max_value=10,
key="best size",
value=5
)
# Initialize session state
if 'scraped_paragraphs' not in st.session_state:
st.session_state.scraped_paragraphs = []
if 'summarizer_mode' not in st.session_state:
st.session_state.summarizer_mode = False
if 'summary' not in st.session_state:
st.session_state.summary = []
app_col = st.columns([2,8,2],gap="small")
with app_col[0]:
pass
with app_col[2]:
pass
with app_col[1]:
# Title
st.write("## GenAi Scraper")
# Input URL
url_input = st.text_input(label="Enter Website URL",key="url input",placeholder="https://www.example.com")
# number of paragraphs
num_paragraphs = st.slider("Select number of paragraphs to scrape", 1, 30, 5)
scrap_btn = st.button("Scrape Paragraphs",key="scrap button")
if url_input.strip() == "" and not scrap_btn:
# animation
particle("animation/particles.html")
else:
if scrap_btn:
st.session_state.scraped_paragraphs = scrape_paragraphs(url_input, num_paragraphs)
st.session_state.summary = [] # Reset summary
# Display scraped paragraphs
if st.session_state.scraped_paragraphs:
st.write("### Scraped Paragraphs")
paragraph_scrap = "\n\n".join(st.session_state.scraped_paragraphs)
st.write(Text_Cleaning(paragraph_scrap))
Copy_Text(Text_Cleaning(paragraph_scrap)) ## copy text
#################### summarizer #############
if select_mode == "Summarizer":
if st.session_state.scraped_paragraphs:
# Toggle for summarization mode
st.session_state.summarizer_mode = st.toggle("Enable Summarizer Mode", st.session_state.summarizer_mode)
if st.session_state.summarizer_mode:
value_func = lambda x: x * 0.3
max_tokens = st.slider(label="Select Max Token Length", min_value=10,
max_value=sum(len(p.split()) for p in st.session_state.scraped_paragraphs),
value=int(value_func(
sum(len(p.split()) for p in st.session_state.scraped_paragraphs)
))
)
if st.button("📄 Generate Summary"):
with st.spinner("Generating Summary..."):
try:
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
st.session_state.summary = summarizer(
Text_Cleaning(" ".join(st.session_state.scraped_paragraphs)),
max_length=max_tokens+20,
min_length=max_tokens,
do_sample=False
)
except Exception as e:
st.warning(f"Error...\n{e}",icon="⚠️")
# Display summary
if st.session_state.summary:
st.write("### Summary")
generated_summary = st.session_state.summary[0]['summary_text']
st.write(generated_summary)
Copy_Text(generated_summary)
################# question answering #####################
elif select_mode == "Que/Ans":
if st.session_state.scraped_paragraphs:
if st.toggle(label="Question Answering",key="Q/A"):
# Inject custom CSS to place the chat input at the bottom
st.markdown(
"""
<style>
/* Fix the chat input box at the bottom */
div[data-testid="stChatInput"] {
position: fixed;
bottom: 0;
margin-bottom: 36px;
}
</style>
""",
unsafe_allow_html=True
)
qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
# Initialize session state
if "messages" not in st.session_state:
st.session_state.messages = []
# User inputs context
context = Text_Cleaning(paragraph_scrap)
# Display chat history
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
if context:
user_input = st.chat_input("💬 Ask a question ",)
if user_input:
with st.chat_message("user"):
st.markdown(user_input)
st.session_state.messages.append({"role": "user", "content": user_input})
with st.spinner("🤔 Thinking..."):
response = qa_pipeline({"question": user_input, "context": context},
max_answer_len=max_answer_length, n_best_size=Best_size)
answer = response["answer"]
with st.chat_message("assistant"):
st.markdown(f"{answer}")
st.session_state.messages.append({"role": "assistant", "content": f"{answer}"})
# Clear chat history button
if st.button("🗑️ Clear Chat"):
st.session_state.messages = []
st.rerun()
# app settings css
insert_css("css_files/app.css") |