Spaces:
Runtime error
Runtime error
File size: 3,963 Bytes
fecd026 |
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 |
import streamlit as st
import llm_part
import os
from langchain_groq import ChatGroq
# Sidebar to select the LLM model
st.sidebar.title("LLM Model Selector")
llm_model = st.sidebar.selectbox("Select LLM Model", ("Google Gemini", "Llama"))
# Define Llama-specific configurations
if llm_model == "Google Gemini": # Check if "Google Gemini" is selected
llm = llm_part.llm_1 # Assign Google Gemini to llm
else:
llm = llm_part.llm_2 # Use the Llama model
# Main app
st.title("Jony's Custom Research Notes Extracted from PDFs Using " + llm_model)
option = st.selectbox("Select PDF Source:", ("Enter URL", "Upload Local File"))
document_text = ""
if option == "Enter URL":
pdf_url = st.text_input("Enter the PDF URL:")
if pdf_url:
try:
with st.spinner("Processing PDF from URL..."):
local_pdf_path = "downloaded_paper.pdf"
llm_part.download_pdf_from_url(pdf_url, local_pdf_path)
document_text = llm_part.extract_text_from_pdf(local_pdf_path)
os.remove(local_pdf_path)
except Exception as e:
st.error(f"Error processing PDF from URL: {e}")
elif option == "Upload Local File":
uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
if uploaded_file is not None:
try:
with st.spinner("Processing uploaded PDF..."):
local_pdf_path = "uploaded_paper.pdf"
with open(local_pdf_path, "wb") as f:
f.write(uploaded_file.read())
document_text = llm_part.extract_text_from_pdf(local_pdf_path)
os.remove(local_pdf_path)
except Exception as e:
st.error(f"Error processing uploaded PDF: {e}")
if document_text:
with st.spinner("Generating the summary..."):
query = llm_part.prompt.format(document_text=document_text[:20000])
result = llm.invoke(query)
st.write("### Summary in Table Format:")
st.write(result.content)
lines = result.content.split('\n')
paragraph_output = []
for line in lines[2:]:
if "|" not in line or not line.strip():
continue
parts = [part.strip() for part in line.split("|") if part.strip()]
if len(parts) == 2:
_, details = parts
if "Not specified" in details or "Not mentioned" in details:
continue
details_clean = llm_part.clean_html_tags(details)
paragraph_output.append(details_clean)
paragraph_output = ". ".join(paragraph_output) + "."
paragraph_output = paragraph_output.replace(" ,", ",").replace(" .", ".")
paragraph_output = paragraph_output.replace(". CNN", ". In this approach, CNN").replace("Federated learning (FL)", "The use of Federated Learning (FL)")
paragraph_output = paragraph_output.replace("The use of Federated Learning", "The study explores the use of Federated Learning")
paragraph_output = paragraph_output.replace("In this approach, CNN", "In this approach, a combination of CNN models was used to enhance performance")
paragraph_output = paragraph_output.replace("achieved", "yielded results indicating")
paragraph_output = paragraph_output.replace("slightly lower", "only marginally lower")
query2 = llm_part.prompt2.format(paragraph=paragraph_output)
result2 = llm.invoke(query2)
st.write("### Answer in Paragraph Style:")
st.markdown("""
<style>
.justified-text {
text-align: justify;
}
</style>
""", unsafe_allow_html=True)
st.markdown(f"<div class='justified-text'>{result2.content}</div>", unsafe_allow_html=True)
#pip install -r requirements.txt
|