Upload 2 files

app.py

@@ -0,0 +1,575 @@
+import os
+import re
+import math
+import tempfile
+from typing import Tuple
+
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+from pypdf import PdfReader
+from docx import Document
+
+
+# =========================
+# Model Configuration
+# =========================
+
+MODEL_ID = os.getenv("MODEL_ID", "Qwen/Qwen2.5-0.5B-Instruct")
+
+MAX_INPUT_CHARS = 12000
+MAX_NEW_TOKENS = 700
+
+
+# =========================
+# Load Local Small LLM
+# =========================
+
+print(f"Loading model: {MODEL_ID}")
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    torch_dtype=torch.float32,
+    device_map="cpu",
+    low_cpu_mem_usage=True,
+)
+
+model.eval()
+
+print("Model loaded successfully.")
+
+
+# =========================
+# File Reading Functions
+# =========================
+
+def read_pdf(file_path: str) -> str:
+    text = ""
+    reader = PdfReader(file_path)
+
+    for i, page in enumerate(reader.pages):
+        page_text = page.extract_text() or ""
+        text += f"\n\n--- Page {i + 1} ---\n{page_text}"
+
+    return text.strip()
+
+
+def read_docx(file_path: str) -> str:
+    doc = Document(file_path)
+    paragraphs = []
+
+    for para in doc.paragraphs:
+        if para.text.strip():
+            paragraphs.append(para.text.strip())
+
+    return "\n".join(paragraphs).strip()
+
+
+def read_txt(file_path: str) -> str:
+    with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
+        return f.read().strip()
+
+
+def extract_text_from_file(file) -> str:
+    if file is None:
+        return ""
+
+    file_path = file.name
+    ext = os.path.splitext(file_path)[1].lower()
+
+    try:
+        if ext == ".pdf":
+            return read_pdf(file_path)
+
+        elif ext == ".docx":
+            return read_docx(file_path)
+
+        elif ext in [".txt", ".md"]:
+            return read_txt(file_path)
+
+        else:
+            return "Unsupported file format. Please upload PDF, DOCX, TXT, or MD."
+    except Exception as e:
+        return f"Error reading file: {str(e)}"
+
+
+# =========================
+# Text Utility
+# =========================
+
+def clean_text(text: str) -> str:
+    text = text.replace("\x00", " ")
+    text = re.sub(r"\n{3,}", "\n\n", text)
+    text = re.sub(r"[ \t]{2,}", " ", text)
+    return text.strip()
+
+
+def limit_text(text: str, max_chars: int = MAX_INPUT_CHARS) -> str:
+    text = clean_text(text)
+
+    if len(text) <= max_chars:
+        return text
+
+    beginning = text[: int(max_chars * 0.65)]
+    ending = text[-int(max_chars * 0.35):]
+
+    return (
+        beginning
+        + "\n\n[... middle part shortened because report is long ...]\n\n"
+        + ending
+    )
+
+
+def estimate_confidence(report_text: str) -> Tuple[int, str]:
+    words = report_text.split()
+    word_count = len(words)
+
+    score = 50
+
+    if word_count > 500:
+        score += 10
+    if word_count > 1200:
+        score += 10
+    if re.search(r"\bmethodology\b|\bmethod\b", report_text, re.I):
+        score += 8
+    if re.search(r"\bresult\b|\bresults\b|\banalysis\b", report_text, re.I):
+        score += 8
+    if re.search(r"\bconclusion\b", report_text, re.I):
+        score += 6
+    if re.search(r"\breference\b|\breferences\b|\bcitation\b", report_text, re.I):
+        score += 5
+    if re.search(r"\bobjective\b|\bgoal\b|\baim\b", report_text, re.I):
+        score += 5
+
+    if word_count < 250:
+        score -= 15
+
+    score = max(20, min(95, score))
+
+    if score >= 80:
+        level = "Strong defense readiness"
+    elif score >= 65:
+        level = "Moderate defense readiness"
+    elif score >= 50:
+        level = "Basic defense readiness"
+    else:
+        level = "Needs more preparation"
+
+    return score, level
+
+
+# =========================
+# Local LLM Function
+# =========================
+
+def ask_local_llm(prompt: str) -> str:
+    messages = [
+        {
+            "role": "system",
+            "content": (
+                "You are Assignment Defense AI. "
+                "Your job is to help students defend their assignments in front of teachers. "
+                "Use simple English. If useful, explain in Bangla-English style. "
+                "Be practical, clear, and exam-focused. "
+                "Do not invent facts that are not in the report."
+            ),
+        },
+        {
+            "role": "user",
+            "content": prompt,
+        },
+    ]
+
+    try:
+        text = tokenizer.apply_chat_template(
+            messages,
+            tokenize=False,
+            add_generation_prompt=True,
+        )
+    except Exception:
+        text = (
+            "System: You are Assignment Defense AI.\n"
+            f"User: {prompt}\n"
+            "Assistant:"
+        )
+
+    inputs = tokenizer(
+        text,
+        return_tensors="pt",
+        truncation=True,
+        max_length=4096,
+    )
+
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=MAX_NEW_TOKENS,
+            temperature=0.4,
+            do_sample=True,
+            top_p=0.9,
+            repetition_penalty=1.12,
+            pad_token_id=tokenizer.eos_token_id,
+        )
+
+    generated_tokens = outputs[0][inputs["input_ids"].shape[-1]:]
+
+    response = tokenizer.decode(
+        generated_tokens,
+        skip_special_tokens=True,
+    )
+
+    return response.strip()
+
+
+# =========================
+# Main AI Features
+# =========================
+
+def generate_defense_pack(file, manual_text: str, difficulty: str, language_style: str):
+    uploaded_text = extract_text_from_file(file)
+    manual_text = manual_text.strip() if manual_text else ""
+
+    if uploaded_text and manual_text:
+        report_text = uploaded_text + "\n\nAdditional Notes:\n" + manual_text
+    elif uploaded_text:
+        report_text = uploaded_text
+    elif manual_text:
+        report_text = manual_text
+    else:
+        return (
+            "Please upload a report or paste your assignment text.",
+            "",
+            "",
+            "",
+            "",
+            "",
+        )
+
+    report_text = limit_text(report_text)
+
+    confidence_score, confidence_level = estimate_confidence(report_text)
+
+    prompt = f"""
+You are preparing a student for assignment defense/viva.
+
+Language style: {language_style}
+Difficulty level: {difficulty}
+
+Here is the student's report:
+
+{report_text}
+
+Create a complete defense preparation pack with these sections:
+
+1. Report Summary
+- Explain the assignment in simple words.
+- Mention the main topic, objective, method, and result if available.
+
+2. 12 Viva Questions
+- Questions should be realistic and teacher-like.
+- Include easy, medium, and challenging questions.
+
+3. Easy Answers
+- Give short, clear answers for each viva question.
+- Answers should sound natural for a student.
+
+4. Defense Speech
+- Write a 1 to 2 minute formal speech for presenting this assignment.
+- Make it confident but not overdramatic.
+
+5. Weak Points Teacher May Ask
+- Identify possible weak areas in the report.
+- Give safe answer strategy for each weak point.
+
+6. Final Preparation Tips
+- Give practical tips before viva.
+"""
+
+    ai_output = ask_local_llm(prompt)
+
+    confidence_report = f"""
+# Confidence Score
+
+**Score:** {confidence_score}/100  
+**Level:** {confidence_level}
+
+## Meaning
+This score is estimated from your report structure, length, and presence of important academic sections.
+
+## How to improve
+- Understand the objective clearly.
+- Memorize the methodology, not the full report.
+- Prepare 5–10 key terms from your assignment.
+- Practice explaining the report in 60 seconds.
+- Be honest if you do not know an answer.
+"""
+
+    summary = ai_output
+    viva_questions = extract_section(ai_output, "12 Viva Questions", "Easy Answers")
+    easy_answers = extract_section(ai_output, "Easy Answers", "Defense Speech")
+    speech = extract_section(ai_output, "Defense Speech", "Weak Points")
+    weak_points = extract_section(ai_output, "Weak Points", "Final Preparation")
+
+    return (
+        summary,
+        viva_questions,
+        easy_answers,
+        speech,
+        weak_points,
+        confidence_report,
+    )
+
+
+def extract_section(text: str, start_keyword: str, end_keyword: str) -> str:
+    try:
+        pattern = rf"(?is){re.escape(start_keyword)}(.*?){re.escape(end_keyword)}"
+        match = re.search(pattern, text)
+
+        if match:
+            return match.group(1).strip()
+
+        return "Section generated inside the full defense pack. Please check the Full Defense Pack tab."
+    except Exception:
+        return "Section extraction failed. Please check the Full Defense Pack tab."
+
+
+def evaluate_practice_answer(question: str, student_answer: str, report_context: str):
+    if not question.strip() or not student_answer.strip():
+        return "Please provide both the viva question and your answer."
+
+    report_context = limit_text(report_context or "", 4000)
+
+    prompt = f"""
+You are a strict but helpful viva teacher.
+
+Report context:
+{report_context}
+
+Viva question:
+{question}
+
+Student answer:
+{student_answer}
+
+Evaluate the answer.
+
+Give:
+1. Score out of 10
+2. What was good
+3. What was weak
+4. Better answer
+5. One short tip for the student
+
+Use simple English.
+"""
+
+    return ask_local_llm(prompt)
+
+
+def create_custom_questions(file, manual_text: str, topic_focus: str, number_of_questions: int):
+    uploaded_text = extract_text_from_file(file)
+    manual_text = manual_text.strip() if manual_text else ""
+
+    report_text = uploaded_text + "\n\n" + manual_text
+    report_text = limit_text(report_text)
+
+    if not report_text.strip():
+        return "Please upload or paste your report first."
+
+    prompt = f"""
+Create {number_of_questions} viva questions from this report.
+
+Focus area: {topic_focus if topic_focus else "overall assignment"}
+
+For each question, include:
+- Question
+- Short easy answer
+- Difficulty: Easy/Medium/Hard
+
+Report:
+{report_text}
+"""
+
+    return ask_local_llm(prompt)
+
+
+# =========================
+# Gradio UI
+# =========================
+
+custom_css = """
+.gradio-container {
+    max-width: 1100px !important;
+    margin: auto !important;
+}
+.main-title {
+    text-align: center;
+    font-size: 34px;
+    font-weight: 800;
+    margin-bottom: 8px;
+}
+.sub-title {
+    text-align: center;
+    font-size: 16px;
+    opacity: 0.85;
+    margin-bottom: 25px;
+}
+"""
+
+with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
+    gr.HTML(
+        """
+        <div class="main-title">Assignment Defense AI</div>
+        <div class="sub-title">
+        Upload your report, get viva questions, easy answers, defense speech, and confidence score.
+        </div>
+        """
+    )
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            file_input = gr.File(
+                label="Upload Report",
+                file_types=[".pdf", ".docx", ".txt", ".md"],
+            )
+
+            manual_text = gr.Textbox(
+                label="Or paste assignment text / notes",
+                placeholder="Paste your assignment text here...",
+                lines=10,
+            )
+
+            difficulty = gr.Radio(
+                choices=["Easy", "Medium", "Hard"],
+                value="Medium",
+                label="Viva Difficulty",
+            )
+
+            language_style = gr.Radio(
+                choices=[
+                    "Simple English",
+                    "Bangla-English Mixed",
+                    "Formal Academic English",
+                ],
+                value="Simple English",
+                label="Answer Style",
+            )
+
+            generate_btn = gr.Button(
+                "Generate Defense Pack",
+                variant="primary",
+            )
+
+        with gr.Column(scale=2):
+            with gr.Tab("Full Defense Pack"):
+                full_output = gr.Markdown()
+
+            with gr.Tab("Viva Questions"):
+                questions_output = gr.Markdown()
+
+            with gr.Tab("Easy Answers"):
+                answers_output = gr.Markdown()
+
+            with gr.Tab("Defense Speech"):
+                speech_output = gr.Markdown()
+
+            with gr.Tab("Weak Points"):
+                weak_output = gr.Markdown()
+
+            with gr.Tab("Confidence Score"):
+                confidence_output = gr.Markdown()
+
+    generate_btn.click(
+        fn=generate_defense_pack,
+        inputs=[file_input, manual_text, difficulty, language_style],
+        outputs=[
+            full_output,
+            questions_output,
+            answers_output,
+            speech_output,
+            weak_output,
+            confidence_output,
+        ],
+    )
+
+    gr.Markdown("---")
+
+    gr.Markdown("## Practice Viva Evaluator")
+
+    with gr.Row():
+        with gr.Column():
+            practice_question = gr.Textbox(
+                label="Viva Question",
+                placeholder="Example: Why did you choose this methodology?",
+                lines=3,
+            )
+
+            practice_answer = gr.Textbox(
+                label="Your Answer",
+                placeholder="Type your answer here...",
+                lines=6,
+            )
+
+            report_context = gr.Textbox(
+                label="Optional Report Context",
+                placeholder="Paste a small part of your report if needed...",
+                lines=6,
+            )
+
+            evaluate_btn = gr.Button("Evaluate My Answer")
+
+        with gr.Column():
+            evaluation_output = gr.Markdown()
+
+    evaluate_btn.click(
+        fn=evaluate_practice_answer,
+        inputs=[practice_question, practice_answer, report_context],
+        outputs=evaluation_output,
+    )
+
+    gr.Markdown("---")
+
+    gr.Markdown("## Custom Viva Question Generator")
+
+    with gr.Row():
+        with gr.Column():
+            topic_focus = gr.Textbox(
+                label="Focus Topic",
+                placeholder="Example: methodology, result, networking, algorithm, water cycle...",
+            )
+
+            number_of_questions = gr.Slider(
+                minimum=5,
+                maximum=25,
+                value=10,
+                step=1,
+                label="Number of Questions",
+            )
+
+            custom_btn = gr.Button("Generate Custom Questions")
+
+        with gr.Column():
+            custom_output = gr.Markdown()
+
+    custom_btn.click(
+        fn=create_custom_questions,
+        inputs=[file_input, manual_text, topic_focus, number_of_questions],
+        outputs=custom_output,
+    )
+
+    gr.Markdown(
+        """
+        ### Notes
+        - This app uses a small local Hugging Face model.
+        - No API key is required.
+        - First run may take time because the model downloads automatically.
+        - For better quality, later you can add Gemini/Groq API as an optional mode.
+        """
+    )
+
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,6 @@
+gradio
+torch
+transformers
+pypdf
+python-docx
+accelerate