Create app.py

app.py

@@ -0,0 +1,231 @@
+import gradio as gr
+import PyPDF2
+import pytesseract
+from PIL import Image
+import io
+import faiss
+import numpy as np
+from transformers import AutoTokenizer, AutoModel
+from docx import Document
+from docx.shared import Inches
+import torch
+import os
+from datetime import datetime
+
+# Initialize models
+MODEL_NAME = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModel.from_pretrained(MODEL_NAME)
+
+# Helper functions
+def extract_text_from_pdf(pdf_file):
+    try:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text() or ""
+        if not text.strip():
+            text = extract_text_with_ocr(pdf_file)
+        return text
+    except Exception as e:
+        return f"Error extracting text: {str(e)} / متن نکالنے میں خرابی: {str(e)}"
+
+def extract_text_with_ocr(pdf_file):
+    try:
+        pdf_reader = PyPDF2.PdfReader(pdf_file)
+        text = ""
+        for page in pdf_reader.pages:
+            img = page.images[0].image if page.images else None
+            if img:
+                text += pytesseract.image_to_string(Image.open(io.BytesIO(img.data)), lang="eng+urd")
+        return text
+    except Exception as e:
+        return f"OCR failed: {str(e)} / OCR ناکام: {str(e)}"
+
+def chunk_text(text, chunk_size=400, overlap=80):
+    words = text.split()
+    chunks = []
+    for i in range(0, len(words), chunk_size - overlap):
+        chunk = " ".join(words[i:i + chunk_size])
+        chunks.append(chunk)
+    return chunks
+
+def create_embeddings(chunks):
+    embeddings = []
+    for chunk in chunks:
+        inputs = tokenizer(chunk, return_tensors="pt", truncation=True, padding=True)
+        with torch.no_grad():
+            embedding = model(**inputs).last_hidden_state.mean(dim=1).numpy()
+        embeddings.append(embedding)
+    return np.vstack(embeddings)
+
+def setup_faiss_index(embeddings):
+    dimension = embeddings.shape[1]
+    index = faiss.IndexFlatL2(dimension)
+    index.add(embeddings)
+    return index
+
+def retrieve_relevant_chunks(query, index, chunks, k=3):
+    query_inputs = tokenizer(query, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        query_embedding = model(**query_inputs).last_hidden_state.mean(dim=1).numpy()
+    distances, indices = index.search(query_embedding, k)
+    return [chunks[i] for i in indices[0]]
+
+def generate_lesson_plan_boppps(grade, subject, topic, slo, duration, context):
+    doc = Document()
+    doc.add_heading(f"Grade {grade} {subject} Lesson Plan: {topic}", 0)
+    doc.add_paragraph(f"SLO: {slo}")
+    doc.add_paragraph(f"Duration: {duration} minutes")
+    doc.add_heading("BOPPPS Model", level=1)
+    doc.add_heading("Bridge-in", level=2)
+    doc.add_paragraph(f"Engaging activity for {topic}: [Generated activity based on {context}]")
+    doc.add_heading("Outcome", level=2)
+    doc.add_paragraph(f"Objective: {slo}")
+    doc.add_heading("Pre-assessment", level=2)
+    doc.add_paragraph("Quick quiz or question to gauge prior knowledge.")
+    doc.add_heading("Participatory Learning", level=2)
+    doc.add_paragraph(f"Interactive activity: [Generated from {context}]")
+    doc.add_heading("Post-assessment", level=2)
+    doc.add_paragraph("Evaluate SLO achievement with a short task.")
+    doc.add_heading("Summary", level=2)
+    doc.add_paragraph("Recap key points of the lesson.")
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    buffer.seek(0)
+    return buffer, "\n".join([p.text for p in doc.paragraphs])
+
+def generate_lesson_plan_backward(grade, subject, topic, slo, duration, context):
+    doc = Document()
+    doc.add_heading(f"Grade {grade} {subject} Lesson Plan: {topic}", 0)
+    doc.add_paragraph(f"SLO: {slo}")
+    doc.add_paragraph(f"Duration: {duration} minutes")
+    doc.add_heading("Backward Design", level=1)
+    doc.add_heading("Desired Results", level=2)
+    doc.add_paragraph(f"Goals: {slo}")
+    doc.add_heading("Acceptable Evidence", level=2)
+    doc.add_paragraph("Assessment criteria based on SLO.")
+    doc.add_heading("Learning Experiences", level=2)
+    doc.add_paragraph(f"Instructional strategies: [Generated from {context}]")
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    buffer.seek(0)
+    return buffer, "\n".join([p.text for p in doc.paragraphs])
+
+def generate_flashcards(grade, subject, topic, slo, context):
+    doc = Document()
+    doc.add_heading(f"Grade {grade} {subject} Flashcards: {topic}", 0)
+    doc.add_paragraph(f"SLO: {slo}")
+    table = doc.add_table(rows=6, cols=2)
+    table.style = "Table Grid"
+    table.cell(0, 0).text = "Front (Question)"
+    table.cell(0, 1).text = "Back (Answer)"
+    for i in range(1, 6):
+        table.cell(i, 0).text = f"Question {i} about {topic}?"
+        table.cell(i, 1).text = f"Answer {i} based on {context}."
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    buffer.seek(0)
+    table_text = "\n".join([f"{row.cells[0].text} | {row.cells[1].text}" for row in table.rows])
+    return buffer, table_text
+
+def generate_worksheet(grade, subject, topic, slo, context):
+    doc = Document()
+    doc.add_heading(f"Grade {grade} {subject} Worksheet: {topic}", 0)
+    doc.add_paragraph(f"SLO: {slo}")
+    doc.add_heading("Instructions", level=1)
+    doc.add_paragraph("Complete the following questions.")
+    doc.add_heading("Multiple Choice", level=2)
+    for i in range(1, 4):
+        doc.add_paragraph(f"{i}. Sample MCQ about {topic}? a) Option1 b) Option2 c) Option3 d) Option4")
+    doc.add_heading("Short Answer", level=2)
+    for i in range(1, 3):
+        doc.add_paragraph(f"{i}. Short answer question about {topic}?")
+    doc.add_heading("Activity", level=2)
+    doc.add_paragraph(f"Activity based on {context}.")
+    buffer = io.BytesIO()
+    doc.save(buffer)
+    buffer.seek(0)
+    return buffer, "\n".join([p.text for p in doc.paragraphs])
+
+# Global variables for FAISS index
+faiss_index = None
+chunks = []
+embeddings = None
+
+def process_and_generate(pdf_file, grade, subject, topic, slo, duration, output_type, feedback=""):
+    global faiss_index, chunks, embeddings
+    if not pdf_file:
+        return None, "Please upload a PDF file / براہ کرم پی ڈی ایف فائل اپ لوڈ کریں", None
+    try:
+        # Extract and process PDF
+        text = extract_text_from_pdf(pdf_file)
+        if "Error" in text or "failed" in text:
+            return None, text, None
+        if not text.strip():
+            return None, "No text extracted. Please upload a valid PDF / کوئی متن نہیں نکالا گیا۔ براہ کرم ایک درست پی ڈی ایف اپ لوڈ کریں", None
+        
+        # Chunk and embed text
+        chunks = chunk_text(text)
+        embeddings = create_embeddings(chunks)
+        faiss_index = setup_faiss_index(embeddings)
+        
+        # Retrieve relevant context
+        query = f"Grade {grade} {subject} {topic} {slo}"
+        relevant_chunks = retrieve_relevant_chunks(query, faiss_index, chunks)
+        context = " ".join(relevant_chunks)
+        
+        # Generate output
+        if output_type == "Lesson Plan (BOPPPS)":
+            buffer, preview = generate_lesson_plan_boppps(grade, subject, topic, slo or "General SLO", duration, context)
+            filename = f"Grade_{grade}_{subject}_BOPPPS_Lesson_Plan.docx"
+        elif output_type == "Lesson Plan (Backward Design)":
+            buffer, preview = generate_lesson_plan_backward(grade, subject, topic, slo or "General SLO", duration, context)
+            filename = f"Grade_{grade}_{subject}_Backward_Design_Lesson_Plan.docx"
+        elif output_type == "Flashcards":
+            buffer, preview = generate_flashcards(grade, subject, topic, slo or "General SLO", context)
+            filename = f"Grade_{grade}_{subject}_Flashcards.docx"
+        else:
+            buffer, preview = generate_worksheet(grade, subject, topic, slo or "General SLO", context)
+            filename = f"Grade_{grade}_{subject}_Worksheet.docx"
+        
+        # Handle feedback
+        if feedback:
+            with open("feedback.txt", "a") as f:
+                f.write(f"{datetime.now()}: {feedback}\n")
+        
+        return buffer, preview, filename
+    except Exception as e:
+        return None, f"Error: {str(e)} / خرابی: {str(e)}", None
+
+# Gradio interface
+with gr.Blocks(title="Curriculum Assistant / نصابی اسسٹنٹ") as demo:
+    gr.Markdown("""
+    # Curriculum Assistant / نصابی اسسٹنٹ
+    Upload a curriculum PDF and generate lesson plans, flashcards, or worksheets / نصابی پی ڈی ایف اپ لوڈ کریں اور سبق کے منصوبے، فلیش کارڈز، یا ورک شیٹس بنائیں.
+    *Tip*: BOPPPS is great for structured lessons; Backward Design focuses on learning goals / BOPPPS منظم اسباق کے لیے بہترین ہے؛ Backward Design سیکھنے کے اہداف پر مرکوز ہے.
+    """)
+    
+    with gr.Row():
+        with gr.Column():
+            pdf_file = gr.File(label="Upload Curriculum PDF / پی ڈی ایف اپ لوڈ کریں", file_types=[".pdf"])
+            grade = gr.Dropdown(choices=list(range(1, 13)), label="Grade / گریڈ")
+            subject = gr.Dropdown(choices=["Math", "Science", "Social Studies", "English"], label="Subject / مضمون")
+            topic = gr.Textbox(label="Topic / موضوع", placeholder="e.g., Photosynthesis / مثلاً، فوٹوسنتھیسز")
+            slo = gr.Textbox(label="Specific SLO (optional) / مخصوص SLO (اختیاری)", placeholder="e.g., Understand cell structure / مثلاً، خلیے کی ساخت کو سمجھیں")
+            duration = gr.Dropdown(choices=[30, 45, 60], label="Lesson Duration (minutes) / سبق کا دورانیہ (منٹ)")
+            output_type = gr.Radio(choices=["Lesson Plan (BOPPPS)", "Lesson Plan (Backward Design)", "Flashcards", "Worksheet"], label="Output Type / آؤٹ پٹ کی قسم")
+            feedback = gr.Textbox(label="Feedback (optional) / رائے (اختیاری)", placeholder="Report issues or suggestions / مسائل یا تجاویز کی اطلاع دیں")
+            submit_button = gr.Button("Generate / بنائیں")
+        
+        with gr.Column():
+            preview = gr.Textbox(label="Preview / پیش منظر", lines=10, interactive=False)
+            download_button = gr.File(label="Download as Word / ورڈ کے طور پر ڈاؤن لوڈ کریں")
+    
+    submit_button.click(
+        fn=process_and_generate,
+        inputs=[pdf_file, grade, subject, topic, slo, duration, output_type, feedback],
+        outputs=[download_button, preview]
+    )
+
+demo.launch()