Create app.py

app.py

@@ -1,93 +1,123 @@
+from dotenv import load_dotenv
+load_dotenv()
 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
-from PyPDF2 import PdfReader
+import torch
+import base64
+
 
+# 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")
 
-# 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):
+#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,
+        model = base_model,
+        tokenizer = tokenizer,
+        max_length = 500,
+        min_length = 50      
     )
+    input_text = file_preprocessing(filepath)
     result = pipe_sum(input_text)
-    return result[0]['summary_text']
+    result = result[0]['summary_text']
+    return result
+def llm_pipleline1(ans):
+    pipe_sum = pipeline(
+        'summarization',
+        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
 
 @st.cache_data
-# Function to display the PDF
-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>'
+# 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
     st.markdown(pdf_display, unsafe_allow_html=True)
 
+#streamlit code
+st.set_page_config(layout='wide')
+
+import os
 
-# Streamlit App
 def main():
-    st.title('PDF Content Summarizer')
+    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 PDF"):
+        if st.button("Summarize"):
             col1, col2 = st.columns(2)
 
-            # Save the uploaded file to a temporary location
-            """with NamedTemporaryFile(delete=False, suffix=".pdf") as temp_file:
+            # 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:
                 temp_file.write(uploaded_file.read())
-                temp_filepath = temp_file.name"""
 
             with col1:
                 st.info("Uploaded PDF File")
-                input_text = extract_text_from_pdf(temp_filepath)
-                
+                pdf_viewer = displayPDF(filepath)
 
             with col2:
-                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)
+                st.info("Summarization is below")
+                summary = llm_pipleline(filepath)
+                st.success(summary)
+    else:
+        st.warning("Please upload a valid PDF file.")
 
-            with col1:
-                st.info("Original Content")
-                st.write(user_input)
 
+    if st.button("text"):
+        ans = input("enter your content")
+        if st.button("Enter"):
+            col1,col2 = st.columns(2)
+
+            with col1:
+                st.info("what you have entered")
+                print(ans)                   
             with col2:
-                st.info("Summarization")
-                summary = llm_pipeline(user_input)
-                st.success(summary)
-        else:
-            st.warning("Please enter some content to summarize.")
+                st.info("Summarization is below")
+                summary1=llm_pipleline1(ans)
+                st.success(summary1)
+
+
 
+                    
+            
 if __name__ == '__main__':
-    main()
+    main()