File size: 3,368 Bytes
a5fd426 2e5199f a5fd426 ffddafd 7cfb0d5 70638ef a5fd426 70638ef 48855de a5fd426 d1d7ee9 a5fd426 703ccd2 a5fd426 48855de a5fd426 48855de a5fd426 11a3e50 a5fd426 11a3e50 |
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 |
import streamlit as st
import pandas as pd
from PIL import Image
import json
from streamlit_lottie import st_lottie
##### BUET Logo ###########
image = Image.open("buet.png")
new_image = image.resize((100, 100))
#st.image(new_image)
st.title("Durghotona GPT: A Web Scraping and Large Language Model Based Framework to Generate Accident Dataset Automatically in Bangladesh")
######### Animation ##########
def load_lottiefile(filepath:str):
with open(filepath,"r") as f:
return json.load(f)
lottie_coding=load_lottiefile("animate.json")
st_lottie(
lottie_coding,
height=200,
)
st.write("**WARNING: Please enter a small number (5-10) for testing purpose. Rule of thumb: It takes almost 20 seconds to process each entry.**")
radio_btn1=st.radio("**Choose the newspaper you want to collect news from**",options=("Prothom Alo","The Daily Star"))
radio_btn2=st.radio("**Choose an LLM model**",options=("GPT-4 (High Cost)","Llama3 (Free)"))
number = st.number_input("**Enter the number of accident news you want the LLM to go through (Maximum 20)**",min_value=0,max_value=20)
url = "https://drive.google.com/file/d/1WvEgAhNHds_Mn2j8SQzdv-9HBXM_BSMD/view?usp=sharing"
if st.button("Generate Dataset"):
st.write("**Please wait while the dataset is being generated. Note that, 'General' accident news reports will be excluded from the dataset. To know more, please read this paper:** [link](%s)" % url)
if radio_btn1=="Prothom Alo":
import Prothom_alo_fully_scraped
df=Prothom_alo_fully_scraped.get_data(number)
elif radio_btn1=="Dhaka Tribune":
import Dhaka_Tribune_Fully_Scraped
df=Dhaka_Tribune_Fully_Scraped.get_data(number)
elif radio_btn1== "The Daily Star":
import Daily_Star_fully_scraped
df=Daily_Star_fully_scraped.get_data(number)
if radio_btn2=="GPT-4 (High Cost)":
import LLM_automation_GPT
df2=LLM_automation_GPT.create_data(df)
elif radio_btn2=="Llama3 (Free)":
import LLM_automation_Groq
df2=LLM_automation_Groq.create_data(df)
elif radio_btn2=="GPT-3.5 (Medium Cost + Long Waiting Time)":
import LLM_automation_GPT35
df2=LLM_automation_GPT35.create_data(df)
st.dataframe(df2)
print(len(df))
st.write("""
**Developed by:**\n
*MD Thamed Bin Zaman Chowdhury, Student ID: 1904184,*\n
*Department of Civil Engineering, BUET*\n
*E-mail: [email protected]*
""")
st.write("--------")
st.write("**Modules and packages used to develop the program:**")
######## Other Logos ################
p=125
image2 = Image.open("pandas.png")
new_image2 = image2.resize((p, p))
image3 = Image.open("numpy.png")
new_image3 = image3.resize((p, p))
image4 = Image.open("selenium_webdriver.jpeg")
new_image4 = image4.resize((p, p))
image5 = Image.open("streamlit.png")
new_image5 = image5.resize((p, p))
image6 = Image.open("openai.png")
new_image6 = image6.resize((p, p))
image7 = Image.open("llama3.jpeg")
new_image7 = image7.resize((p, p))
image8 = Image.open("langchain.png")
new_image8 = image8.resize((p, p))
image9 = Image.open("deep_translator.png")
new_image9 = image9.resize((p, p))
st.image([new_image2, new_image3,new_image4,new_image5,new_image6,new_image7,new_image8,new_image9]) |