File size: 2,865 Bytes
955df66 8a4bc78 955df66 4441659 955df66 25fc809 955df66 6868e46 955df66 c8974f6 955df66 |
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 |
import streamlit as st
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import PyPDFLoader
import time
from transformers import T5Tokenizer, T5ForConditionalGeneration
from transformers import pipeline
import torch
import base64
# Model and tokenizer
#model_checkpoint = "LaMini-Flan-T5-248M"
model_checkpoint = "MBZUAI/LaMini-Flan-T5-783M"
model_tokenizer = T5Tokenizer.from_pretrained(model_checkpoint)
#model = T5ForConditionalGeneration.from_pretrained(model_checkpoint, device_map='auto', torch_dtype=torch.float32)
model = T5ForConditionalGeneration.from_pretrained(model_checkpoint)
#REPO_ID = "MBZUAI/LaMini-Flan-T5-783M"
#model = pipeline(task='summarization', model=REPO_ID, token=access_token)
# File loader and preprocessing
def preprocess_pdf(file):
loader = PyPDFLoader(file)
pages = loader.load_and_split()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=170, chunk_overlap=70)
texts = text_splitter.split_documents(pages)
final_text = ""
for text in texts:
final_text = final_text + text.page_content
return final_text
# Language Model pipeline
def language_model_pipeline(filepath):
summarization_pipeline = pipeline(
'summarization',
model=model,
tokenizer=model_tokenizer,
max_length=500,
min_length=70)
input_text = preprocess_pdf(filepath)
summary_result = summarization_pipeline(input_text)
summarized_text = summary_result[0]['summary_text']
return summarized_text
@st.cache_data
# Function to display the PDF content
def display_pdf(file):
with open(file, "rb") as f:
base64_pdf = base64.b64encode(f.read()).decode('utf-8')
pdf_display = f'<embed src="data:application/pdf;base64,{base64_pdf}" width="700" height="1000" type="application/pdf">'
st.markdown(pdf_display, unsafe_allow_html=True)
# Streamlit code
st.set_page_config(layout="wide")
def main():
st.title("Document Summarization App using Language Model")
uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf'])
if uploaded_file is not None:
if st.button("Summarize"):
col1, col2 = st.columns(2)
filepath = uploaded_file.name
with open(filepath, "wb") as temp_file:
temp_file.write(uploaded_file.read())
with col1:
st.info("Uploaded File")
pdf_view = display_pdf(filepath)
with col2:
prg = st.progress(0)
for i in range(100):
time.sleep(0.1)
prg.progress(i+1)
summarized_result = language_model_pipeline(filepath)
st.info("Summarization Complete")
st.success(summarized_result)
if __name__ == "__main__":
main() |