""import gradio as gr
import pandas as pd
import matplotlib.pyplot as plt
import torch
from transformers import T5Tokenizer, T5ForConditionalGeneration
from sentence\_transformers import SentenceTransformer, util
import numpy as np

# ------------------------------

# Offline Quiz Generator

# ------------------------------

model\_qg = T5ForConditionalGeneration.from\_pretrained("t5-base")
tokenizer\_qg = T5Tokenizer.from\_pretrained("t5-base")

def generate\_mcqs(text, num\_questions=3):
input\_text = f"generate questions: {text}"
input\_ids = tokenizer\_qg.encode(input\_text, return\_tensors="pt", max\_length=512, truncation=True)
outputs = model\_qg.generate(input\_ids=input\_ids, max\_length=256, num\_return\_sequences=1)
return tokenizer\_qg.decode(outputs\[0], skip\_special\_tokens=True).strip()

# ------------------------------

# Weakness Analyzer

# ------------------------------

def analyze\_weakness(csv\_file):
df = pd.read\_csv(csv\_file.name)
summary = df.groupby("Topic")\["Score"].mean().sort\_values()
return summary.to\_string()

# ------------------------------

# Teaching Assistant

# ------------------------------

def chatbot\_response(message, history):
return "This is a placeholder response for now. (LLM not integrated)"

# ------------------------------

# Speech Question Solver

# ------------------------------

def speech\_answer(audio):
return "Audio to text transcription + answer generation is not included in offline version."

# ------------------------------

# PDF/YT Summarizer

# ------------------------------

def summarize\_text(text):
input\_text = f"summarize: {text.strip()}"
input\_ids = tokenizer\_qg.encode(input\_text, return\_tensors="pt", max\_length=512, truncation=True)
summary\_ids = model\_qg.generate(input\_ids, max\_length=150, min\_length=30, length\_penalty=5., num\_beams=2)
return tokenizer\_qg.decode(summary\_ids\[0], skip\_special\_tokens=True)

# ------------------------------

# Engagement Predictor (Mock)

# ------------------------------

def predict\_engagement(file):
df = pd.read\_csv(file.name)
avg\_time = df\['TimeSpent'].mean()
if avg\_time < 10:
return "⚠️ Risk of disengagement"
else:
return "✅ Engaged student"

# ------------------------------

# Badge Generator

# ------------------------------

def generate\_badge(file):
df = pd.read\_csv(file.name)
avg\_score = df\['Score'].mean()
if avg\_score >= 80:
return "🏅 Gold Badge"
elif avg\_score >= 50:
return "🥈 Silver Badge"
else:
return "🥉 Bronze Badge"

# ------------------------------

# Translator (Mock - offline)

# ------------------------------

def translate\_text(text, target\_lang):
return f"(Translated to {target\_lang}) - This is a mock translation."

# ------------------------------

# Plagiarism Checker

# ------------------------------

model\_plag = SentenceTransformer('all-MiniLM-L6-v2')

def check\_plagiarism(text1, text2):
emb1 = model\_plag.encode(text1, convert\_to\_tensor=True)
emb2 = model\_plag.encode(text2, convert\_to\_tensor=True)
score = util.cos\_sim(emb1, emb2).item()
return f"Similarity Score: {score:.2f} - {'⚠️ Possible Plagiarism' if score > 0.8 else '✅ Looks Original'}"

# ------------------------------

# Gradio UI

# ------------------------------

with gr.Blocks() as demo:
gr.Markdown("# 📚 AI-Powered LMS Suite (Offline Mode)")

```
with gr.Tab("🧠 Quiz Generator"):
    quiz_text = gr.Textbox(label="Content", lines=5)
    quiz_slider = gr.Slider(1, 10, value=3, label="Number of Questions")
    quiz_btn = gr.Button("Generate Quiz")
    quiz_out = gr.Textbox(label="Generated Quiz")
    quiz_btn.click(fn=generate_mcqs, inputs=[quiz_text, quiz_slider], outputs=quiz_out)

with gr.Tab("📉 Weakness Analyzer"):
    weak_file = gr.File(label="Upload CSV with Topic & Score columns")
    weak_btn = gr.Button("Analyze")
    weak_out = gr.Textbox(label="Analysis")
    weak_btn.click(fn=analyze_weakness, inputs=weak_file, outputs=weak_out)

with gr.Tab("🤖 Teaching Assistant"):
    chat = gr.ChatInterface(fn=chatbot_response)

with gr.Tab("🎤 Speech Q Solver"):
    audio_in = gr.Audio(source="microphone", type="filepath")
    audio_btn = gr.Button("Answer")
    audio_out = gr.Textbox()
    audio_btn.click(fn=speech_answer, inputs=audio_in, outputs=audio_out)

with gr.Tab("📄 Summarizer"):
    sum_text = gr.Textbox(lines=5, label="Paste Text")
    sum_btn = gr.Button("Summarize")
    sum_out = gr.Textbox(label="Summary")
    sum_btn.click(fn=summarize_text, inputs=sum_text, outputs=sum_out)

with gr.Tab("📊 Engagement Predictor"):
    eng_file = gr.File(label="Upload CSV with TimeSpent column")
    eng_btn = gr.Button("Predict")
    eng_out = gr.Textbox()
    eng_btn.click(fn=predict_engagement, inputs=eng_file, outputs=eng_out)

with gr.Tab("🏅 Badge Generator"):
    badge_file = gr.File(label="Upload CSV with Score column")
    badge_btn = gr.Button("Get Badge")
    badge_out = gr.Textbox()
    badge_btn.click(fn=generate_badge, inputs=badge_file, outputs=badge_out)

with gr.Tab("🌍 Translator"):
    trans_in = gr.Textbox(label="Enter Text")
    trans_lang = gr.Textbox(label="Target Language")
    trans_btn = gr.Button("Translate")
    trans_out = gr.Textbox()
    trans_btn.click(fn=translate_text, inputs=[trans_in, trans_lang], outputs=trans_out)

with gr.Tab("📋 Plagiarism Checker"):
    text1 = gr.Textbox(label="Text 1", lines=3)
    text2 = gr.Textbox(label="Text 2", lines=3)
    plag_btn = gr.Button("Check Similarity")
    plag_out = gr.Textbox()
    plag_btn.click(fn=check_plagiarism, inputs=[text1, text2], outputs=plag_out)
```

# Launch app

demo.launch()