Create app.py

app.py

@@ -0,0 +1,915 @@
+# ============================================================
+# 📦 IMPORTS
+# ============================================================
+
+import re
+import os
+import json
+import faiss
+import gradio as gr
+import numpy as np
+import pandas as pd
+import requests
+
+from sentence_transformers import SentenceTransformer
+from groq import Groq
+
+
+# ============================================================
+# 🔑 GROQ API KEY
+# ============================================================
+
+GROQ_API_KEY = os.getenv('GRAPI')
+
+client = Groq(api_key=GROQ_API_KEY)
+
+
+# ============================================================
+# 📘 GOOGLE DOC LOADER
+# ============================================================
+
+DOC_ID = "1utErkC3Xa8hhiQul7tzil9SjRydGEKGEBpVgaCp6qXM"
+
+def load_google_doc():
+
+    url = f"https://docs.google.com/document/d/{DOC_ID}/export?format=txt"
+
+    text = requests.get(url).text
+
+    return text
+
+
+raw_text = load_google_doc()
+
+
+# ============================================================
+# 📚 SPLIT CHAPTERS
+# ============================================================
+
+def split_units(text):
+
+    units = {}
+
+    splits = re.split(r"(UNIT\s+\d+.*?)\n", text, flags=re.I)
+
+    for i in range(1, len(splits), 2):
+
+        title = splits[i].strip()
+
+        content = splits[i+1]
+
+        units[title] = content
+
+    return units
+
+
+units_data = split_units(raw_text)
+
+print("✅ Loaded Units:")
+print(list(units_data.keys()))
+
+
+# ============================================================
+# 🔍 EMBEDDING MODEL
+# ============================================================
+
+embedding_model = SentenceTransformer(
+    "all-MiniLM-L6-v2"
+)
+
+
+# ============================================================
+# ✂️ CHUNKING
+# ============================================================
+
+def chunk_text(text, chunk_size=150):
+
+    words = text.split()
+
+    chunks = []
+
+    for i in range(0, len(words), chunk_size):
+
+        chunk = " ".join(words[i:i+chunk_size])
+
+        chunks.append(chunk)
+
+    return chunks
+
+
+all_chunks = []
+chunk_unit_map = []
+
+for unit, text in units_data.items():
+
+    chunks = chunk_text(text)
+
+    all_chunks.extend(chunks)
+
+    chunk_unit_map.extend([unit]*len(chunks))
+
+
+# ============================================================
+# 🧠 CREATE FAISS VECTOR DB
+# ============================================================
+
+embeddings = embedding_model.encode(all_chunks)
+
+if len(embeddings.shape) == 1:
+
+    embeddings = np.expand_dims(embeddings, axis=0)
+
+dimension = embeddings.shape[1]
+
+index = faiss.IndexFlatL2(dimension)
+
+index.add(np.array(embeddings).astype("float32"))
+
+print("✅ FAISS INDEX READY")
+
+
+# ============================================================
+# 🔍 RETRIEVE CONTEXT
+# ============================================================
+
+def retrieve_context(question, unit):
+
+    q_embedding = embedding_model.encode([question])
+
+    D, I = index.search(
+        np.array(q_embedding).astype("float32"),
+        5
+    )
+
+    retrieved = []
+
+    for idx in I[0]:
+
+        if chunk_unit_map[idx] == unit:
+
+            retrieved.append(all_chunks[idx])
+
+    return "\n".join(retrieved)
+
+
+# ============================================================
+# 🤖 GROQ HELPER
+# ============================================================
+
+def groq_call(prompt):
+
+    completion = client.chat.completions.create(
+
+        model="llama-3.3-70b-versatile",
+
+        messages=[
+            {
+                "role": "user",
+                "content": prompt
+            }
+        ],
+
+        temperature=0.5
+    )
+
+    return completion.choices[0].message.content
+
+
+# ============================================================
+# 📚 VOCAB EXTRACTION
+# ============================================================
+
+def extract_vocabulary(unit):
+
+    context = units_data[unit][:7000]
+
+    prompt = f"""
+You are an FSC English linguistic AI.
+
+Extract ONLY 5 important contextual vocabulary words.
+
+Return STRICT JSON:
+
+[
+ {{
+   "word":"...",
+   "meaning_en":"...",
+   "meaning_ur":"...",
+   "context_sentence":"..."
+ }}
+]
+
+TEXT:
+{context}
+"""
+
+    result = groq_call(prompt)
+
+    try:
+
+        data = json.loads(result)
+
+        return data
+
+    except:
+
+        return []
+
+
+# ============================================================
+# 🧠 METACOGNITIVE ENGINE
+# ============================================================
+
+student_analytics = []
+
+
+def build_mcq(word_data):
+
+    word = word_data["word"]
+
+    meaning = word_data["meaning_en"]
+
+    prompt = f"""
+Create one FSC-level MCQ.
+
+Word: {word}
+Meaning: {meaning}
+
+Return STRICT JSON:
+
+{{
+ "question":"...",
+ "options": {{
+   "A":"...",
+   "B":"...",
+   "C":"..."
+ }},
+ "answer":"A/B/C"
+}}
+"""
+
+    result = groq_call(prompt)
+
+    try:
+
+        return json.loads(result)
+
+    except:
+
+        return None
+
+
+# ============================================================
+# 🎯 PROCESS ANSWER
+# ============================================================
+
+def evaluate_answer(
+    word,
+    correct_answer,
+    selected_answer,
+    confidence
+):
+
+    correct = selected_answer == correct_answer
+
+    feedback = ""
+
+    autonomy_points = 0
+
+    if correct:
+
+        if confidence <= 2:
+
+            feedback = (
+                f"✅ Correct! "
+                f"You were unsure, but contextual clues helped you."
+            )
+
+        elif confidence >= 4:
+
+            feedback = (
+                f"🔥 Excellent! "
+                f"You understood the lexical context confidently."
+            )
+
+        autonomy_points += 10
+
+    else:
+
+        if confidence >= 4:
+
+            feedback = (
+                f"⚠️ High confidence but incorrect answer.\n"
+                f"You may need stronger contextual inference."
+            )
+
+        else:
+
+            feedback = (
+                f"❌ Incorrect.\n"
+                f"Try analyzing surrounding contextual clues."
+            )
+
+    student_analytics.append({
+
+        "word": word,
+
+        "correct": correct,
+
+        "confidence": confidence
+    })
+
+    return feedback, autonomy_points
+
+
+# ============================================================
+# 🌉 BILINGUAL SCAFFOLD
+# ============================================================
+
+def scaffold(word_data, level):
+
+    if level == 1:
+
+        return f"""
+🧠 English Scaffold:
+
+{word_data['meaning_en']}
+"""
+
+    if level == 2:
+
+        return f"""
+🧠 Urdu Scaffold:
+
+{word_data['meaning_ur']}
+"""
+
+    return ""
+
+
+# ============================================================
+# 📊 ANALYTICS DASHBOARD
+# ============================================================
+
+def generate_dashboard():
+
+    if len(student_analytics) == 0:
+
+        return pd.DataFrame()
+
+    df = pd.DataFrame(student_analytics)
+
+    return df
+
+
+# ============================================================
+# 🎨 CUSTOM CSS
+# ============================================================
+
+custom_css = """
+
+/* =========================
+   GLOBAL
+========================= */
+
+body{
+    background:#F1F5F9 !important;
+    font-family:'Inter',sans-serif;
+    color:#111827 !important;
+}
+
+/* =========================
+   MAIN APP CONTAINER
+========================= */
+
+.gradio-container{
+    max-width:1200px !important;
+    margin:auto !important;
+
+    background:white !important;
+
+    border-radius:24px;
+
+    padding:35px !important;
+
+    box-shadow:
+    0px 8px 30px rgba(0,0,0,0.08);
+
+    color:#111827 !important;
+}
+
+
+/* =========================
+   TITLES
+========================= */
+
+.main-title{
+    text-align:center;
+
+    font-size:52px;
+
+    font-weight:800;
+
+    color:#0F172A !important;
+
+    margin-bottom:8px;
+}
+
+.subtitle{
+    text-align:center;
+
+    font-size:20px;
+
+    color:#475569 !important;
+
+    margin-bottom:35px;
+}
+
+
+/* =========================
+   CARDS
+========================= */
+
+.card{
+    background:#FFFFFF !important;
+
+    border:1px solid #E2E8F0 !important;
+
+    border-radius:20px;
+
+    padding:22px;
+
+    margin-bottom:22px;
+
+    box-shadow:
+    0px 2px 12px rgba(0,0,0,0.05);
+}
+
+
+/* =========================
+   TEXT COLORS
+========================= */
+
+h1,h2,h3,h4,h5,h6{
+    color:#0F172A !important;
+}
+
+p,span,div,label{
+    color:#111827 !important;
+}
+
+
+/* =========================
+   TARGET WORD
+========================= */
+
+.target-word{
+    font-size:40px;
+
+    font-weight:700;
+
+    color:#0284C7 !important;
+
+    margin-bottom:10px;
+}
+
+.context-text{
+    font-size:18px;
+
+    line-height:1.8;
+
+    color:#1E293B !important;
+}
+
+
+/* =========================
+   SECTION LABELS
+========================= */
+
+.section-label{
+    display:inline-block;
+
+    background:#E0F2FE;
+
+    color:#0369A1 !important;
+
+    padding:8px 14px;
+
+    border-radius:10px;
+
+    font-size:15px;
+
+    font-weight:700;
+
+    margin-bottom:16px;
+}
+
+
+/* =========================
+   INPUTS
+========================= */
+
+textarea,
+input,
+select{
+
+    background:#FFFFFF !important;
+
+    color:#111827 !important;
+
+    border:1.5px solid #CBD5E1 !important;
+
+    border-radius:12px !important;
+
+    padding:12px !important;
+
+    font-size:16px !important;
+}
+
+
+/* =========================
+   DROPDOWN
+========================= */
+
+.gr-dropdown{
+    color:#111827 !important;
+}
+
+
+/* =========================
+   RADIO BUTTONS
+========================= */
+
+.gr-radio label{
+
+    background:#F8FAFC !important;
+
+    border:1px solid #CBD5E1 !important;
+
+    border-radius:12px;
+
+    padding:12px 16px;
+
+    margin-right:10px;
+
+    transition:0.2s;
+}
+
+.gr-radio label:hover{
+    background:#E0F2FE !important;
+}
+
+
+/* =========================
+   BUTTONS
+========================= */
+
+button{
+
+    background:#0EA5E9 !important;
+
+    color:white !important;
+
+    border:none !important;
+
+    border-radius:14px !important;
+
+    font-size:17px !important;
+
+    font-weight:700 !important;
+
+    padding:14px 22px !important;
+
+    transition:0.25s ease;
+}
+
+button:hover{
+
+    background:#0284C7 !important;
+
+    transform:translateY(-1px);
+}
+
+
+/* =========================
+   SLIDER
+========================= */
+
+input[type="range"]{
+    accent-color:#0EA5E9 !important;
+}
+
+
+/* =========================
+   OUTPUT BOXES
+========================= */
+
+.output-box{
+
+    background:#F8FAFC !important;
+
+    border:1px solid #E2E8F0 !important;
+
+    border-radius:16px;
+
+    padding:18px;
+
+    color:#111827 !important;
+}
+
+
+/* =========================
+   CHATBOT / MARKDOWN
+========================= */
+
+.markdown-text{
+    color:#111827 !important;
+}
+
+
+/* =========================
+   MOBILE RESPONSIVE
+========================= */
+
+@media(max-width:768px){
+
+    .main-title{
+        font-size:34px;
+    }
+
+    .subtitle{
+        font-size:16px;
+    }
+
+    .target-word{
+        font-size:28px;
+    }
+
+    .context-text{
+        font-size:16px;
+    }
+
+    .gradio-container{
+        padding:18px !important;
+    }
+}
+
+"""
+
+
+# ============================================================
+# 🚀 UI FUNCTIONS
+# ============================================================
+
+current_vocab = []
+current_mcq = None
+current_word_data = None
+
+
+def load_chapter(unit):
+
+    global current_vocab
+    global current_word_data
+    global current_mcq
+
+    current_vocab = extract_vocabulary(unit)
+
+    if len(current_vocab) == 0:
+
+        return (
+            "❌ Could not extract vocabulary.",
+            "",
+            gr.update(choices=[]),
+            ""
+        )
+
+    current_word_data = current_vocab[0]
+
+    current_mcq = build_mcq(current_word_data)
+
+    vocab_text = f"""
+# 📘 Target Word
+
+### {current_word_data['word']}
+
+### Context Sentence:
+{current_word_data['context_sentence']}
+"""
+
+    return (
+
+        vocab_text,
+
+        current_mcq["question"],
+
+        gr.update(
+            choices=list(
+                current_mcq["options"].values()
+            )
+        ),
+
+        ""
+    )
+
+
+def submit_answer(selected, confidence):
+
+    global current_mcq
+    global current_word_data
+
+    options = current_mcq["options"]
+
+    reverse_map = {
+        v:k for k,v in options.items()
+    }
+
+    selected_letter = reverse_map[selected]
+
+    feedback, points = evaluate_answer(
+
+        current_word_data["word"],
+
+        current_mcq["answer"],
+
+        selected_letter,
+
+        confidence
+    )
+
+    return f"""
+# 🧠 Feedback
+
+{feedback}
+
+⭐ Autonomy Points: {points}
+"""
+
+
+def show_english_scaffold():
+
+    global current_word_data
+
+    return scaffold(current_word_data, 1)
+
+
+def show_urdu_scaffold():
+
+    global current_word_data
+
+    return scaffold(current_word_data, 2)
+
+
+def show_dashboard():
+
+    df = generate_dashboard()
+
+    return df
+
+
+# ============================================================
+# 🌟 GRADIO UI
+# ============================================================
+
+with gr.Blocks(
+    css=custom_css,
+    theme=gr.themes.Soft()
+) as demo:
+
+    gr.HTML("""
+    <div class='main-title'>
+    🚀 LexiMetrica
+    </div>
+
+    <div class='subtitle'>
+    AI Metacognitive Lexical Enhancement Framework
+    </div>
+    """)
+
+    with gr.Row():
+
+        chapter_dropdown = gr.Dropdown(
+
+            choices=list(units_data.keys()),
+
+            label="📚 Select Chapter"
+        )
+
+        load_btn = gr.Button(
+            "Load Chapter",
+            variant="primary"
+        )
+
+    with gr.Row():
+
+        vocab_output = gr.Markdown()
+
+    with gr.Row():
+
+        mcq_question = gr.Markdown()
+
+    with gr.Row():
+
+        mcq_radio = gr.Radio(
+            choices=[],
+            label="Choose Meaning"
+        )
+
+    confidence_slider = gr.Slider(
+
+        minimum=1,
+
+        maximum=5,
+
+        step=1,
+
+        label="🧠 Confidence Level"
+    )
+
+    submit_btn = gr.Button(
+        "Submit Answer",
+        variant="primary"
+    )
+
+    feedback_output = gr.Markdown()
+
+    gr.Markdown("---")
+
+    gr.Markdown("## 🌉 Need a Bridge?")
+
+    with gr.Row():
+
+        english_btn = gr.Button(
+            "English Scaffold"
+        )
+
+        urdu_btn = gr.Button(
+            "Urdu Scaffold"
+        )
+
+    scaffold_output = gr.Markdown()
+
+    gr.Markdown("---")
+
+    dashboard_btn = gr.Button(
+        "📊 Show Analytics Dashboard"
+    )
+
+    dashboard_output = gr.Dataframe()
+
+    # ======================================
+    # EVENTS
+    # ======================================
+
+    load_btn.click(
+
+        fn=load_chapter,
+
+        inputs=chapter_dropdown,
+
+        outputs=[
+            vocab_output,
+            mcq_question,
+            mcq_radio,
+            scaffold_output
+        ]
+    )
+
+    submit_btn.click(
+
+        fn=submit_answer,
+
+        inputs=[
+            mcq_radio,
+            confidence_slider
+        ],
+
+        outputs=feedback_output
+    )
+
+    english_btn.click(
+
+        fn=show_english_scaffold,
+
+        outputs=scaffold_output
+    )
+
+    urdu_btn.click(
+
+        fn=show_urdu_scaffold,
+
+        outputs=scaffold_output
+    )
+
+    dashboard_btn.click(
+
+        fn=show_dashboard,
+
+        outputs=dashboard_output
+    )
+
+
+# ============================================================
+# 🚀 LAUNCH
+# ============================================================
+
+demo.launch(debug=True)