app.py

import streamlit as st
import openai
import nltk
nltk.download('punkt')
import PyPDF2
import string

# st.write("ok")
# Set up OpenAI API credentials
openai.api_key = "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"



def read_pdf(fname):
    
    reader = PyPDF2.PdfReader(fname)
    text_ext = []
    for i in range(len(reader.pages)):
        pageObj = reader.pages[i]
        # extracting text from page
        text_ext.append(pageObj.extract_text())

    return text_ext

def clean_text(text):
    if isinstance(text, list):
        text = " ".join(text)
    text = text.lower()
    text = text.translate(str.maketrans("", "", string.punctuation))
    text = " ".join(text.split())
    return text

def generate_keywords(text):
    num_keywords = 6
    cleaned_text = text.strip()
  
    response = openai.Completion.create(
        engine="text-davinci-002",
        prompt=f"What are {num_keywords} highly related keywords for the following text?\n{cleaned_text}\n\nKeywords:",
        max_tokens=50,
        n=1,
        stop=None,
        temperature=0.5,
        best_of=num_keywords,
    )

    generated_text = response.choices[0].text.strip()

    keywords = generated_text.split(',')

    st.write("Top Keywords:")
    for i, keyword in enumerate(keywords[:num_keywords]):
        st.write(f"{i+1}. {keyword.strip()}")

def generate_summary(text):
    summary_length = 2

    cleaned_text = text.strip()

    response = openai.Completion.create(
        engine="text-davinci-002",
        prompt=f"Please summarize the following text in {summary_length} sentences:\n{cleaned_text}\n\nSummary:",
        max_tokens=100,
        n=1,
        stop=None,
        temperature=0.5,
    )

    generated_text = response.choices[0].text.strip()
    st.write("Description:")
    sentences = nltk.sent_tokenize(generated_text)
    for sentence in sentences:
      st.write(sentence)

# Main Streamlit app
st.title("Meta Magic")

uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")

if uploaded_file is not None:
    # Read PDF file and extract text
    pages = read_pdf(uploaded_file)
    text = clean_text(pages)

    # Generate keywords and summary
    if st.button("Generate Keywords"):
        generate_keywords(text)
    
    if st.button("Generate Summary"):
        generate_summary(text)