Create app.py

app.py

@@ -0,0 +1,154 @@
+import gradio as gr
+import PyPDF2
+from transformers import pipeline
+import random
+import re
+from io import BytesIO
+
+# Initialize models (CPU-optimized)
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn", device=-1)
+qa_generator = pipeline("text2text-generation", model="google/flan-t5-base", device=-1)
+
+def extract_text_from_pdf(pdf_file):
+    """Extract text from uploaded PDF"""
+    try:
+        pdf_reader = PyPDF2.PdfReader(BytesIO(pdf_file))
+        text = ""
+        # Limit to first 10 pages for CPU performance
+        max_pages = min(10, len(pdf_reader.pages))
+        for page_num in range(max_pages):
+            text += pdf_reader.pages[page_num].extract_text()
+        return text[:15000]  # Limit tokens
+    except Exception as e:
+        return f"Error reading PDF: {str(e)}"
+
+def chunk_text(text, max_length=1000):
+    """Split text into manageable chunks"""
+    words = text.split()
+    chunks = []
+    current_chunk = []
+    current_length = 0
+    
+    for word in words:
+        current_length += len(word) + 1
+        if current_length > max_length:
+            chunks.append(" ".join(current_chunk))
+            current_chunk = [word]
+            current_length = len(word)
+        else:
+            current_chunk.append(word)
+    
+    if current_chunk:
+        chunks.append(" ".join(current_chunk))
+    return chunks
+
+def generate_summary(text):
+    """Generate concise summary"""
+    if len(text) < 100:
+        return "Text too short to summarize."
+    
+    chunks = chunk_text(text, 1000)
+    summaries = []
+    
+    for chunk in chunks[:3]:  # Limit chunks for CPU
+        try:
+            summary = summarizer(chunk, max_length=130, min_length=30, do_sample=False)
+            summaries.append(summary[0]['summary_text'])
+        except:
+            continue
+    
+    return "\n\n".join(summaries) if summaries else "Unable to generate summary."
+
+def generate_flashcards(text, num_cards=5):
+    """Generate flashcards from text"""
+    sentences = [s.strip() for s in text.split('.') if len(s.strip()) > 20]
+    selected = random.sample(sentences, min(num_cards, len(sentences)))
+    
+    flashcards = []
+    for i, sentence in enumerate(selected, 1):
+        # Extract key concept (simple heuristic)
+        words = sentence.split()
+        if len(words) > 5:
+            question = f"Q{i}: What is explained by: '{' '.join(words[:5])}...'?"
+            answer = sentence
+            flashcards.append(f"**{question}**\n\nA: {answer}\n")
+    
+    return "\n---\n\n".join(flashcards) if flashcards else "Unable to generate flashcards."
+
+def generate_quiz(text, num_questions=3):
+    """Generate multiple choice quiz"""
+    sentences = [s.strip() for s in text.split('.') if len(s.strip()) > 30]
+    selected = random.sample(sentences, min(num_questions, len(sentences)))
+    
+    quiz = []
+    for i, sentence in enumerate(selected, 1):
+        prompt = f"Create a multiple choice question about: {sentence[:200]}"
+        try:
+            result = qa_generator(prompt, max_length=100)
+            quiz.append(f"**Question {i}:**\n{result[0]['generated_text']}\n")
+        except:
+            quiz.append(f"**Question {i}:**\nBased on the text: {sentence[:150]}... (provide your answer)\n")
+    
+    return "\n---\n\n".join(quiz) if quiz else "Unable to generate quiz."
+
+def process_document(pdf_file, text_input, features):
+    """Main processing function"""
+    # Get text from PDF or text input
+    if pdf_file is not None:
+        text = extract_text_from_pdf(pdf_file)
+    elif text_input.strip():
+        text = text_input[:15000]
+    else:
+        return "Please provide a PDF file or paste text.", "", "", ""
+    
+    if text.startswith("Error"):
+        return text, "", "", ""
+    
+    # Generate outputs based on selected features
+    summary = generate_summary(text) if "Summary" in features else ""
+    flashcards = generate_flashcards(text) if "Flashcards" in features else ""
+    quiz = generate_quiz(text) if "Quiz" in features else ""
+    
+    return text[:500] + "..." if len(text) > 500 else text, summary, flashcards, quiz
+
+# Gradio Interface
+with gr.Blocks(theme=gr.themes.Soft(), title="StudyForge AI") as demo:
+    gr.Markdown("""
+    # 📚 StudyForge AI - Your Intelligent Study Companion
+    Transform any textbook chapter or notes into summaries, flashcards, and practice quizzes instantly!
+    """)
+    
+    with gr.Row():
+        with gr.Column():
+            pdf_input = gr.File(label="Upload PDF (Max 10 pages)", file_types=[".pdf"])
+            text_input = gr.Textbox(label="Or Paste Text Here", lines=5, placeholder="Paste your study material...")
+            
+            features = gr.CheckboxGroup(
+                ["Summary", "Flashcards", "Quiz"],
+                label="Select What You Need",
+                value=["Summary", "Flashcards"]
+            )
+            
+            generate_btn = gr.Button("🚀 Generate Study Materials", variant="primary")
+        
+        with gr.Column():
+            text_preview = gr.Textbox(label="Text Preview", lines=3)
+            summary_output = gr.Markdown(label="Summary")
+            flashcards_output = gr.Markdown(label="Flashcards")
+            quiz_output = gr.Markdown(label="Practice Quiz")
+    
+    generate_btn.click(
+        fn=process_document,
+        inputs=[pdf_input, text_input, features],
+        outputs=[text_preview, summary_output, flashcards_output, quiz_output]
+    )
+    
+    gr.Markdown("""
+    ### Tips:
+    - For best results, use clear, well-formatted text (10 pages max for CPU performance)
+    - Flashcards work best with content that has clear concepts
+    - Processing may take 30-60 seconds on CPU
+    """)
+
+if __name__ == "__main__":
+    demo.launch()