Create app.py

app.py

@@ -1,15 +1,10 @@
-from dotenv import load_dotenv
-load_dotenv()
-from tempfile import NamedTemporaryFile
 import os
+import base64
+from tempfile import NamedTemporaryFile
 import streamlit as st
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import PyPDFLoader,DirectoryLoader
-from langchain.chains.summarize import load_summarize_chain
 from transformers import pipeline
-import torch
-import base64
-
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
@@ -17,7 +12,7 @@ from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
 base_model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
 
-#file loader and processing 
+# File loader and processing
 def file_preprocessing(file):
     loader = PyPDFLoader(file)
     pages = loader.load_and_split()
@@ -25,60 +20,37 @@ def file_preprocessing(file):
     texts = text_splitter.split_documents(pages)
     final_texts = ""
     for text in texts:
-        print(text)
-        final_texts = final_texts + text.page_content
+        final_texts += text.page_content
     return final_texts
 
-#lm pipeline
-def llm_pipleline(filepath):
-    pipe_sum = pipeline(
-        'summarization',
-        model = base_model,
-        tokenizer = tokenizer,
-        max_length = 500,
-        min_length = 50      
-    )
-    input_text = file_preprocessing(filepath)
-    result = pipe_sum(input_text)
-    result = result[0]['summary_text']
-    return result
-def llm_pipleline1(ans):
+# LLM pipeline for summarization
+def llm_pipeline(input_text):
     pipe_sum = pipeline(
         'summarization',
-        model = base_model,
-        tokenizer = tokenizer,
-        max_length = 500,
-        min_length = 50      
+        model=base_model,
+        tokenizer=tokenizer,
+        max_length=500,
+        min_length=50,
     )
-    input_text =""+ ans
     result = pipe_sum(input_text)
-    result = result[0]['summary_text']
-    return result
+    return result[0]['summary_text']
 
 @st.cache_data
 # Function to display the PDF file
-def displayPDF(file):
-    # Opening file from file path
-    with open(file, "rb") as f:
-        base_pdf = base64.b64encode(f.read()).decode('utf-8')  # Corrected function name and variable
-
-    # Embedding PDF in HTML
-    pdf_display = f'<iframe src="data:application/pdf;base64,{base_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
-    
-    # Displaying the file
+def displayPDF(file_path):
+    with open(file_path, "rb") as f:
+        base64_pdf = base64.b64encode(f.read()).decode('utf-8')
+    pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="600" type="application/pdf"></iframe>'
     st.markdown(pdf_display, unsafe_allow_html=True)
 
-
-#streamlit code
-st.set_page_config(layout='wide')
-
+# Streamlit App
 def main():
     st.title('Content Summarizer')
 
+    # PDF Upload Section
     uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf'])
-
     if uploaded_file is not None:
-        if st.button("Summarize"):
+        if st.button("Summarize PDF"):
             col1, col2 = st.columns(2)
 
             # Save the uploaded file to a temporary location
@@ -88,17 +60,17 @@ def main():
 
             with col1:
                 st.info("Uploaded PDF File")
-                pdf_viewer = displayPDF(temp_filepath)
+                displayPDF(temp_filepath)
 
             with col2:
-                st.info("Summarization is below")
-                summary = llm_pipleline(temp_filepath)
+                st.info("Summarization")
+                input_text = file_preprocessing(temp_filepath)
+                summary = llm_pipeline(input_text)
                 st.success(summary)
 
-    # New Section for Text Input Summarization
+    # Text Input Section
     st.header("Summarize Your Text")
     user_input = st.text_area("Enter your content here:", height=200)
-
     if st.button("Summarize Text"):
         if user_input.strip():
             col1, col2 = st.columns(2)
@@ -108,8 +80,8 @@ def main():
                 st.write(user_input)
 
             with col2:
-                st.info("Summarization is below")
-                summary = llm_pipleline1(user_input)
+                st.info("Summarization")
+                summary = llm_pipeline(user_input)
                 st.success(summary)
         else:
             st.warning("Please enter some content to summarize.")