Doctore-AI / app.py
Shanulhaq's picture
Update app.py
935599b verified
raw
history blame
2.1 kB
import streamlit as st
import subprocess
import sys
# Function to install packages if not already installed
def install_package(package_name):
subprocess.check_call([sys.executable, "-m", "pip", "install", package_name])
# Install required packages if not already installed
try:
import pdfplumber
except ModuleNotFoundError:
install_package('pdfplumber')
try:
from transformers import pipeline
except ModuleNotFoundError:
install_package('transformers')
from transformers import pipeline
# Ensure that either PyTorch or TensorFlow is installed
try:
import torch
except ModuleNotFoundError:
install_package('torch')
import torch
# Function to extract text from PDFs using pdfplumber
def extract_text_from_pdfs(pdf_files):
pdf_texts = {}
for pdf_file in pdf_files:
with pdfplumber.open(pdf_file) as pdf:
text = ""
for page in pdf.pages:
text += page.extract_text()
pdf_texts[pdf_file.name] = text
return pdf_texts
# Load pre-trained QA model
qa_pipeline = pipeline('question-answering', model='distilbert-base-uncased-distilled-squad')
# Function to answer questions based on extracted text
def answer_question(pdf_texts, question):
context = " ".join(pdf_texts.values())
result = qa_pipeline(question=question, context=context)
return result['answer']
# Streamlit application
st.title("PDF Question Answering App")
# File uploader for PDF files
uploaded_files = st.file_uploader("Upload PDF files", type="pdf", accept_multiple_files=True)
# Display uploaded files
if uploaded_files:
# Extract text from PDFs
pdf_texts = extract_text_from_pdfs(uploaded_files)
st.write("PDFs Uploaded Successfully!")
# Question input
question = st.text_input("Enter your question:")
if st.button("Get Answer"):
if question:
answer = answer_question(pdf_texts, question)
st.write(f"Answer: {answer}")
else:
st.write("Please enter a question.")
else:
st.write("Please upload PDF files to continue.")