File size: 1,891 Bytes
955df66
 
 
 
 
 
 
1c19d29
 
6665931
1c19d29
955df66
 
 
a6f5220
f6818d0
955df66
 
 
 
 
 
 
 
 
 
 
22b1490
955df66
6ca90ab
955df66
 
 
 
6ca90ab
e3b62d5
955df66
 
 
 
 
22b1490
 
 
aa01ead
22b1490
 
 
 
6ca90ab
22b1490
 
 
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
import streamlit as st 
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import PyPDFLoader
from transformers import T5Tokenizer, T5ForConditionalGeneration
from transformers import pipeline
import torch
import base64
from PIL import Image

st.image("https://huggingface.co/spaces/wiwaaw/summary/resolve/main/banner.png")

# Model and tokenizer 
model_checkpoint = "MBZUAI/LaMini-Flan-T5-783M"
model_tokenizer = T5Tokenizer.from_pretrained(model_checkpoint)
model = T5ForConditionalGeneration.from_pretrained(model_checkpoint)

# 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

@st.cache_data
# Language Model pipeline
def language_model_pipeline(filepath):
    summarization_pipeline = pipeline(
        'summarization',
        model=model,
        tokenizer=model_tokenizer,
        max_length=500, 
        min_length=32)
    input_text = preprocess_pdf(filepath)
    summary_result = summarization_pipeline(input_text)
    summarized_text = summary_result[0]['summary_text']
    return summarized_text

title = st.title("PDF Summarization using LaMini")
uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf'])
if uploaded_file is not None:
    st.success("File Uploaded")
    if st.button("Summarize"):
        filepath = uploaded_file.name
        with open(filepath, "wb") as temp_file:
            temp_file.write(uploaded_file.read())
            
        summarized_result = language_model_pipeline(filepath)
        st.info("Summarization Complete")
        st.success(summarized_result)