Update app.py

app.py

@@ -1,8 +1,10 @@
 import streamlit as st
 import io
 import PyPDF2
-from transformers import pipeline
+from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor, pipeline
 from gtts import gTTS
+from PIL import Image
+from pdf2image import convert_from_bytes
 
 # Function to extract text from a PDF
 def extract_text_from_pdf(pdf_file):
@@ -13,19 +15,33 @@ def extract_text_from_pdf(pdf_file):
         text += page.extract_text() or ""  # Handle None for non-text pages
     return text
 
-# Function to generate discussion points
+# Function to generate discussion points (summarization)
 def generate_discussion_points(text):
-    summarizer = pipeline('summarization')
+    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
     summary = summarizer(text, max_length=600, min_length=300, do_sample=False)
-    return summary[0]['summary_text']
+    return summary[0]["summary_text"]
 
 # Function to convert text to speech
 def text_to_speech(text):
-    tts = gTTS(text=text, lang='en')
+    tts = gTTS(text=text, lang="en")
     tts.save("discussion_points.mp3")
 
+# Function for document question answering
+def answer_questions(pdf_file, question):
+    images = convert_from_bytes(pdf_file.read())
+    processor = Pix2StructProcessor.from_pretrained("google/pix2struct-docvqa-large")
+    model = Pix2StructForConditionalGeneration.from_pretrained("google/pix2struct-docvqa-large")
+    
+    answers = []
+    for img in images:
+        inputs = processor(images=img, text=question, return_tensors="pt")
+        outputs = model.generate(**inputs)
+        answer = processor.decode(outputs[0], skip_special_tokens=True)
+        answers.append(answer)
+    return answers
+
 # Streamlit app
-st.title("PDF Analysis and Discussion Generator")
+st.title("PDF Analysis Tool: Text, Summarization, and Q&A")
 uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
 
 if uploaded_file is not None:
@@ -36,11 +52,21 @@ if uploaded_file is not None:
 
     # Generate and display discussion points
     st.subheader("Generated Discussion Points")
-    discussion_points = generate_discussion_points(text)
-    st.write(discussion_points)
-
-    # Convert discussion points to audio and play it
-    text_to_speech(discussion_points)
-    audio_file = open("discussion_points.mp3", "rb")
-    audio_bytes = audio_file.read()
-    st.audio(audio_bytes, format="audio/mp3")
+    if st.button("Generate Discussion Points"):
+        discussion_points = generate_discussion_points(text)
+        st.write(discussion_points)
+        text_to_speech(discussion_points)
+
+        # Play the audio
+        audio_file = open("discussion_points.mp3", "rb")
+        audio_bytes = audio_file.read()
+        st.audio(audio_bytes, format="audio/mp3")
+
+    # Q&A Section
+    st.subheader("Document Question Answering")
+    question = st.text_input("Ask a question about the document:")
+    if question:
+        answers = answer_questions(uploaded_file, question)
+        st.write("Answers:")
+        for page_num, answer in enumerate(answers, 1):
+            st.write(f"Page {page_num}: {answer}")