Create app.py (#9)

- Create app.py (cadce87da2c4ca52675a5dce4205d2e88034c2a7)

app.py

@@ -1,123 +1,92 @@
-from dotenv import load_dotenv
-load_dotenv()
 import os
+import base64
+import tempfile
 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 PyPDF2 import PdfReader
 
-# Load model directly
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
+# Load the summarization model
 tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
 base_model = AutoModelForSeq2SeqLM.from_pretrained("MBZUAI/LaMini-Flan-T5-248M")
 
-#file loader and processing 
-def file_preprocessing(file):
-    loader = PyPDFLoader(file)
-    pages = loader.load_and_split()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
-    texts = text_splitter.split_documents(pages)
-    final_texts = ""
-    for text in texts:
-        print(text)
-        final_texts = 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):
+# Function to extract text from a PDF using PyPDF2
+def extract_text_from_pdf(pdf_path):
+      reader = PdfReader(pdf_path)
+      text = ""
+      for page in reader.pages:
+          text += page.extract_text()  # Extract text from each page
+      if not text.strip():
+          raise ValueError("The PDF file contains no extractable text.")
+      return text
+
+
+# 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>'
+# Function to display the PDF
+def displayPDF(file_path):
     
-    # Displaying the file
-    st.markdown(pdf_display, unsafe_allow_html=True)
+      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')
-
-import os
 
+# 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)
 
-            # Ensure the directory exists
-            data_dir = "data"
-            if not os.path.exists(data_dir):
-                os.makedirs(data_dir)
-
-            filepath = os.path.join(data_dir, uploaded_file.name)
-            with open(filepath, 'wb') as temp_file:
+            # Save the uploaded file to a temporary location
+            with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf", dir="/tmp/") as temp_file:
                 temp_file.write(uploaded_file.read())
+                temp_filepath = temp_file.name
 
             with col1:
                 st.info("Uploaded PDF File")
-                pdf_viewer = displayPDF(filepath)
+                displayPDF(temp_filepath)
 
             with col2:
-                st.info("Summarization is below")
-                summary = llm_pipleline(filepath)
-                st.success(summary)
-    else:
-        st.warning("Please upload a valid PDF file.")
-
-
-    if st.button("text"):
-        ans = input("enter your content")
-        if st.button("Enter"):
-            col1,col2 = st.columns(2)
+                st.info("Summarization")
+                input_text = extract_text_from_pdf(temp_filepath)
+                if input_text:  # Proceed only if text extraction was successful
+                    summary = llm_pipeline(input_text)
+                    st.success(summary)
+
+    # 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)
 
             with col1:
-                st.info("what you have entered")
-                print(ans)                   
-            with col2:
-                st.info("Summarization is below")
-                summary1=llm_pipleline1(ans)
-                st.success(summary1)
-
+                st.info("Original Content")
+                st.write(user_input)
 
+            with col2:
+                st.info("Summarization")
+                summary = llm_pipeline(user_input)
+                st.success(summary)
+        else:
+            st.warning("Please enter some content to summarize.")
 
-                    
-            
 if __name__ == '__main__':
-    main()            
+    main()