Stable deployment version: Lazy loading and Docker optimized

.gitattributes

@@ -0,0 +1,3 @@
+templates/**/*.html linguist-vendored
+static/**/* linguist-vendored
+*.pth filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,10 @@
+.venv/
+__pycache__/
+*.pyc
+static/uploads/*
+!static/uploads/.gitkeep
+# models/*.pth
+.vscode/
+pip_list.txt
+*.mp3
+dataset/

Dockerfile

@@ -0,0 +1,31 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    libasound2-dev \
+    portaudio19-dev \
+    libportaudio2 \
+    libportaudiocpp0 \
+    ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy the requirements file into the container
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose the port the app runs on (Hugging Face uses 7860)
+EXPOSE 7860
+
+# Command to run the application with increased timeout for model loading
+# We use 0.0.0.0 to make it accessible outside the container
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--timeout", "300", "--workers", "1", "app:app"]

Procfile

@@ -0,0 +1 @@
+web: gunicorn app:app

README.md

@@ -0,0 +1,30 @@
+---
+title: AML Project - AI Services Hub
+emoji: 🤖
+colorFrom: blue
+colorTo: purple
+sdk: docker
+app_port: 7860
+pinned: false
+---
+
+# AI Services Hub
+
+A comprehensive Flask-based platform integrating diverse AI models for Image Classification, NLP (Translation, Text Gen, Sentiment), Audio Intelligence (Voice STT/TTS), and Data Mining (Clustering & Association Rules).
+
+## Features
+
+- **Gender Classification**: Custom PyTorch CNN model
+- **Text Generation**: GPT-2 powered text completion
+- **Translation**: English to Urdu translation
+- **Sentiment Analysis**: Voice-enabled sentiment detection
+- **Question Answering**: Voice-to-voice QA system
+- **Zero-Shot Classification**: Custom label classification
+- **Clustering**: K-Means and DBSCAN algorithms
+- **Association Rules**: A-priori market basket analysis
+
+## Tech Stack
+
+- Flask, PyTorch, Hugging Face Transformers
+- Scikit-learn, Pandas, Matplotlib
+- OpenAI Whisper, gTTS, Librosa

app.py

@@ -0,0 +1,449 @@
+from flask import Flask, render_template, request
+from werkzeug.utils import secure_filename
+import os
+import numpy as np
+from PIL import Image
+from transformers import pipeline
+from gtts import gTTS
+import speech_recognition as sr
+import librosa
+
+# Try importing tensorflow, handle if missing
+try:
+    from tensorflow.keras.models import load_model
+except ImportError:
+    load_model = None
+
+app = Flask(__name__)
+app.config['UPLOAD_FOLDER'] = 'static/uploads'
+os.makedirs(app.config['UPLOAD_FOLDER'], exist_ok=True)
+
+# Dataset paths (Colab format - update these for local use)
+TRAIN_DIR = "/content/drive/MyDrive/AML-F24/Code/image_datset/image_datset/train"
+TEST_DIR = "/content/drive/MyDrive/AML-F24/Code/image_datset/image_datset/test"
+
+# ---------------- MODELS ---------------- #
+from models_loader import loader
+
+sentiment_model = loader.sentiment_pipeline
+qa_model = loader.qa_pipeline
+textgen_model = loader.text_gen_pipeline
+translator = loader.translator_pipeline
+stt_model = loader.stt_pipeline
+zsl_model = loader.zsl_pipeline
+gender_classifier = loader.gender_classifier
+gender_model = loader.cnn_model # Custom CNN
+
+# Clustering Dependencies
+import pandas as pd
+from sklearn.cluster import KMeans, DBSCAN
+import matplotlib
+matplotlib.use('Agg') # Non-interactive backend
+import matplotlib.pyplot as plt
+import io
+import base64
+from sklearn.preprocessing import StandardScaler
+
+# Association Rules Dependencies
+from mlxtend.frequent_patterns import apriori, association_rules
+from mlxtend.preprocessing import TransactionEncoder
+
+# ---------------- ROUTES ---------------- #
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+# -------- GENDER CLASSIFICATION -------- #
+@app.route('/gender', methods=['GET', 'POST'])
+def gender():
+    result = ""
+    if request.method == 'POST':
+        if 'image' not in request.files:
+            return render_template('gender.html', result="No image uploaded")
+        
+        file = request.files['image']
+        if file.filename == '':
+            return render_template('gender.html', result="No image selected")
+
+        if file:
+            # Save file temporarily (use secure filename)
+            filename = secure_filename(file.filename)
+            filepath = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+            file.save(filepath)
+
+            if gender_classifier:
+                try:
+                    img = Image.open(filepath)
+                    results = gender_classifier(img)
+                    # Extract the top result
+                    result = results[0]['label'].capitalize()
+                    print(f"Gender Classification Result: {result}")
+                except Exception as e:
+                    result = f"Error processing image with transformers: {e}"
+            elif gender_model:
+                try:
+                    img = Image.open(filepath).convert('RGB')
+                    img = img.resize((128, 128))
+                    img_array = np.array(img).astype(np.float32) / 255.0
+                    # Correct shape for PyTorch CNN: (batch, channels, height, width)
+                    img_tensor = torch.from_numpy(img_array).permute(2, 0, 1).unsqueeze(0)
+                    
+                    with torch.no_grad():
+                        prediction = gender_model(img_tensor)
+                    result = "Male" if prediction.item() > 0.5 else "Female"
+                except Exception as e:
+                    import traceback
+                    print(traceback.format_exc())
+                    result = f"Error processing image: {e}"
+            else:
+                result = "Gender model is not loaded (check console for details)."
+            
+    return render_template('gender.html', result=result)
+
+# -------- TEXT GENERATION -------- #
+@app.route('/textgen', methods=['GET', 'POST'])
+def textgen():
+    result = ""
+    if request.method == 'POST':
+        text = request.form['prompt']
+        if textgen_model:
+            result = textgen_model(text, max_length=50)[0]['generated_text']
+        else:
+            result = "Text generation model not available"
+    return render_template('textgen.html', generated_text=result)
+
+# -------- TRANSLATION -------- #
+@app.route('/translate', methods=['GET', 'POST'])
+def translate():
+    result = ""
+    if request.method == 'POST':
+        text = request.form.get('text', '')
+        if translator:
+            result = translator(text)[0]['translation_text']
+        else:
+            result = "Translation model not available"
+    return render_template('translate.html', translated_text=result)
+
+# -------- SENTIMENT (VOICE) -------- #
+@app.route('/sentiment', methods=['GET', 'POST'])
+def sentiment():
+    result = ""
+    if request.method == 'POST':
+        typed_text = request.form.get('text', '').strip()
+        audio_file = request.files.get('voice')
+        
+        text = ""
+        if typed_text:
+            text = typed_text
+        elif audio_file:
+            if audio_file.filename == '':
+                return render_template('sentiment.html', result="No audio selected")
+            audio_filename = secure_filename(audio_file.filename)
+            audio_path = os.path.join(app.config['UPLOAD_FOLDER'], audio_filename)
+            audio_file.save(audio_path)
+            
+            if stt_model is None:
+                return render_template('sentiment.html', result="STT model not available")
+            
+            try:
+                audio_array, sampling_rate = librosa.load(audio_path, sr=16000)
+                # Ensure the audio array is 1D and float32
+                audio_array = audio_array.astype(np.float32)
+                stt_result = stt_model(audio_array)
+                text = stt_result.get('text', '').strip()
+                if not text:
+                     return render_template('sentiment.html', result="Could not understand audio")
+            except Exception as e:
+                return render_template('sentiment.html', result=f"STT processing error: {str(e)}")
+        else:
+            return render_template('sentiment.html', result="No input provided")
+
+        # Sentiment Analysis Logic
+        if sentiment_model is None:
+            result = f"Analyzed: {text} | Status: Sentiment model not available"
+        else:
+            try:
+                sentiment_data = sentiment_model(text)[0]
+                label = sentiment_data.get('label', 'Unknown').capitalize()
+                score = round(sentiment_data.get('score', 0) * 100, 1)
+                
+                # Question Detection
+                questions_words = ["who", "what", "where", "when", "why", "how", "is", "are", "do", "does", "can", "could", "would", "should"]
+                is_question = text.strip().endswith("?") or any(text.lower().startswith(q + " ") for q in questions_words)
+                
+                type_str = "Question" if is_question else "Statement"
+                result = f"Text: \"{text}\" | Type: {type_str} | Sentiment: {label} (Confidence: {score}%)"
+            except Exception as e:
+                result = f"Sentiment analysis failed: {str(e)}"
+                
+    return render_template('sentiment.html', result=result)
+
+# -------- QUESTION ANSWERING (VOICE → VOICE) -------- #
+@app.route('/qa', methods=['GET', 'POST'])
+def qa():
+    answer = ""
+    context = ""
+    question_text = ""
+    if request.method == 'POST':
+        context = request.form.get('context', '')
+        audio_file = request.files.get('voice')
+        typed_question = request.form.get('question', '').strip()
+
+        if typed_question:
+            question_text = typed_question
+        elif audio_file:
+            if audio_file.filename != '':
+                audio_filename = secure_filename(audio_file.filename)
+                audio_path = os.path.join(app.config['UPLOAD_FOLDER'], audio_filename)
+                audio_file.save(audio_path)
+                
+                try:
+                    audio_array, sampling_rate = librosa.load(audio_path, sr=16000)
+                    audio_array = audio_array.astype(np.float32)
+                    stt_result = stt_model(audio_array)
+                    question_text = stt_result.get('text', '').strip()
+                except Exception as e:
+                    print(f"STT Error in QA: {e}")
+                    answer = "Error processing your voice question."
+
+        if not answer and question_text and context:
+            if qa_model is None:
+                answer = "Question-answering model not available"
+            else:
+                try:
+                    result = qa_model(question=question_text, context=context)
+                    answer = result.get('answer', str(result))
+                    
+                    try:
+                        tts = gTTS(answer)
+                        tts.save(os.path.join('static', 'answer.mp3'))
+                    except Exception as e:
+                        print(f"TTS failed: {e}")
+                except Exception as e:
+                    answer = f"QA model error: {e}"
+        elif not answer:
+            answer = "Please provide both context and a question (typed or voice)."
+
+    return render_template('qa.html', answer=answer, context=context, question=question_text)
+
+# -------- ZERO-SHOT LEARNING -------- #
+@app.route('/zsl', methods=['GET', 'POST'])
+def zsl():
+    result = None
+    if request.method == 'POST':
+        text = request.form.get('text', '')
+        labels = request.form.get('labels', '')
+        
+        if not text or not labels:
+            return render_template('zsl.html', error="Both text and labels are required.")
+            
+        candidate_labels = [l.strip() for l in labels.split(',') if l.strip()]
+        
+        if zsl_model is None:
+            return render_template('zsl.html', error="ZSL model not available.")
+            
+        try:
+            output = zsl_model(text, candidate_labels=candidate_labels)
+            # Find the index of the label with the highest score
+            best_idx = np.argmax(output['scores'])
+            result = {
+                'label': output['labels'][0], # BART-MNLI returns sorted
+                'score': round(output['scores'][0] * 100, 2),
+                'all_results': zip(output['labels'], [round(s * 100, 2) for s in output['scores']])
+            }
+        except Exception as e:
+            return render_template('zsl.html', error=f"ZSL error: {str(e)}")
+            
+    return render_template('zsl.html', result=result)
+
+
+# -------- K-MEANS CLUSTERING -------- #
+@app.route('/clustering', methods=['GET', 'POST'])
+def clustering():
+    plot_url = None
+    cluster_info = None
+    if request.method == 'POST':
+        if 'file' not in request.files:
+            return render_template('clustering.html', error="No file uploaded")
+            
+        file = request.files['file']
+        n_clusters = int(request.form.get('clusters', 3))
+        
+        if file.filename == '':
+            return render_template('clustering.html', error="No file selected")
+            
+        try:
+            if file.filename.endswith('.csv'):
+                df = pd.read_csv(file)
+            else:
+                df = pd.read_excel(file)
+                
+            # Keep only numeric columns
+            numeric_df = df.select_dtypes(include=[np.number])
+            
+            if numeric_df.shape[1] < 2:
+                return render_template('clustering.html', error="Dataset must have at least 2 numeric columns for clustering.")
+                
+            # Basic cleaning
+            numeric_df = numeric_df.dropna()
+            
+            # K-Means
+            kmeans = KMeans(n_clusters=n_clusters, random_state=42)
+            df['Cluster'] = kmeans.fit_predict(numeric_df)
+            
+            # Create Plot (using first two numeric columns)
+            plt.figure(figsize=(10, 6))
+            scatter = plt.scatter(numeric_df.iloc[:, 0], numeric_df.iloc[:, 1], c=df['Cluster'], cmap='viridis', alpha=0.6)
+            plt.colorbar(scatter, label='Cluster')
+            plt.title(f'K-Means Clustering (K={n_clusters})')
+            plt.xlabel(numeric_df.columns[0])
+            plt.ylabel(numeric_df.columns[1])
+            plt.grid(True, alpha=0.3)
+            
+            # Save plot to base64
+            img = io.BytesIO()
+            plt.savefig(img, format='png', bbox_inches='tight', transparent=True)
+            img.seek(0)
+            plot_url = base64.b64encode(img.getvalue()).decode()
+            plt.close()
+            
+            # Cluster stats
+            cluster_info = df.groupby('Cluster').size().to_dict()
+            
+        except Exception as e:
+            return render_template('clustering.html', error=f"Clustering error: {str(e)}")
+            
+    return render_template('clustering.html', plot_url=plot_url, cluster_info=cluster_info)
+
+# -------- DBSCAN CLUSTERING -------- #
+@app.route('/dbscan', methods=['GET', 'POST'])
+def dbscan():
+    plot_url = None
+    cluster_info = None
+    if request.method == 'POST':
+        if 'file' not in request.files:
+            return render_template('dbscan.html', error="No file uploaded")
+            
+        file = request.files['file']
+        eps = float(request.form.get('eps', 0.5))
+        min_samples = int(request.form.get('min_samples', 5))
+        
+        if file.filename == '':
+            return render_template('dbscan.html', error="No file selected")
+            
+        try:
+            if file.filename.endswith('.csv'):
+                df = pd.read_csv(file)
+            else:
+                df = pd.read_excel(file)
+                
+            # Keep only numeric columns
+            numeric_df = df.select_dtypes(include=[np.number])
+            
+            if numeric_df.shape[1] < 2:
+                return render_template('dbscan.html', error="Dataset must have at least 2 numeric columns for clustering.")
+                
+            # Basic cleaning
+            numeric_df = numeric_df.dropna()
+            
+            # DBSCAN with Scaling
+            scaler = StandardScaler()
+            scaled_data = scaler.fit_transform(numeric_df)
+            
+            dbscan_model = DBSCAN(eps=eps, min_samples=min_samples)
+            df['Cluster'] = dbscan_model.fit_predict(scaled_data)
+            
+            # Create Plot
+            plt.figure(figsize=(10, 6))
+            scatter = plt.scatter(numeric_df.iloc[:, 0], numeric_df.iloc[:, 1], c=df['Cluster'], cmap='viridis', alpha=0.6)
+            plt.colorbar(scatter, label='Cluster')
+            plt.title(f'DBSCAN Clustering (eps={eps}, min_samples={min_samples}) - Scaled')
+            plt.xlabel(numeric_df.columns[0])
+            plt.ylabel(numeric_df.columns[1])
+            plt.grid(True, alpha=0.3)
+            
+            # Save plot to base64
+            img = io.BytesIO()
+            plt.savefig(img, format='png', bbox_inches='tight', transparent=True)
+            img.seek(0)
+            plot_url = base64.b64encode(img.getvalue()).decode()
+            plt.close()
+            
+            # Cluster stats
+            cluster_info = df.groupby('Cluster').size().to_dict()
+            
+        except Exception as e:
+            return render_template('dbscan.html', error=f"DBSCAN error: {str(e)}")
+            
+    return render_template('dbscan.html', plot_url=plot_url, cluster_info=cluster_info)
+
+# -------- A-PRIORI ASSOCIATION RULES -------- #
+@app.route('/apriori', methods=['GET', 'POST'])
+def apriori_route():
+    rules_html = None
+    if request.method == 'POST':
+        if 'file' not in request.files:
+            return render_template('apriori.html', error="No file uploaded")
+            
+        file = request.files['file']
+        min_support = float(request.form.get('min_support', 0.1))
+        min_threshold = float(request.form.get('min_threshold', 0.7))
+        metric = request.form.get('metric', 'lift')
+        has_header = request.form.get('has_header') == 'on'
+        
+        if file.filename == '':
+            return render_template('apriori.html', error="No file selected")
+            
+        try:
+            if file.filename.endswith('.csv'):
+                df = pd.read_csv(file, header=0 if has_header else None)
+            else:
+                df = pd.read_excel(file, header=0 if has_header else None)
+            
+            # Convert to list of lists (transactions) - Handle nulls and whitespace
+            transactions = []
+            values = df.values.tolist()
+            for row in values:
+                # Filter out nan, None, and empty strings, and convert everything to string
+                transaction = sorted(list(set([str(item).strip() for item in row if pd.notna(item) and str(item).strip() != ''])))
+                if transaction:
+                    transactions.append(transaction)
+            
+            if not transactions:
+                 return render_template('apriori.html', error="No valid transactions found in file.")
+
+            # Transaction Encoding
+            te = TransactionEncoder()
+            te_ary = te.fit(transactions).transform(transactions)
+            encoded_df = pd.DataFrame(te_ary, columns=te.columns_)
+            
+            # Generate Frequent Itemsets
+            frequent_itemsets = apriori(encoded_df, min_support=min_support, use_colnames=True)
+            
+            if frequent_itemsets.empty:
+                return render_template('apriori.html', error="No frequent itemsets found. Try lowering min support.")
+                
+            # Generate Rules
+            rules = association_rules(frequent_itemsets, metric=metric, min_threshold=min_threshold)
+            
+            if rules.empty:
+                return render_template('apriori.html', error=f"No rules found for {metric} >= {min_threshold}. Try lowering threshold.")
+            
+            # Format rules for display
+            rules['antecedents'] = rules['antecedents'].apply(lambda x: list(x))
+            rules['consequents'] = rules['consequents'].apply(lambda x: list(x))
+            
+            # Selection of columns for display
+            display_rules = rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']]
+            rules_html = display_rules.to_dict(orient='records')
+            
+        except Exception as e:
+            import traceback
+            print(traceback.format_exc())
+            return render_template('apriori.html', error=f"A-priori error: {str(e)}")
+            
+    return render_template('apriori.html', rules=rules_html)
+
+if __name__ == '__main__':
+    app.run(debug=True, use_reloader=False)

models/gender_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecaa25fc7866baa1f67478d0785f17621d9f1eb00bf29abe94a985617a92e62
+size 16859283

models_loader.py

@@ -0,0 +1,159 @@
+from transformers import pipeline
+import torch
+import torch.nn as nn
+import os
+import numpy as np
+from PIL import Image
+
+class GenderCNN(nn.Module):
+    def __init__(self):
+        super(GenderCNN, self).__init__()
+        self.conv_layers = nn.Sequential(
+            nn.Conv2d(3, 32, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(32),
+            nn.MaxPool2d(2, 2),
+            nn.Conv2d(32, 64, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.MaxPool2d(2, 2),
+            nn.Conv2d(64, 128, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(128),
+            nn.MaxPool2d(2, 2)
+        )
+        self.fc_layers = nn.Sequential(
+            nn.Flatten(),
+            nn.Linear(128 * 16 * 16, 256),
+            nn.ReLU(),
+            nn.Dropout(0.5),
+            nn.Linear(256, 1),
+            nn.Sigmoid()
+        )
+
+    def forward(self, x):
+        x = self.conv_layers(x)
+        x = self.fc_layers(x)
+        return x
+
+class ModelLoader:
+    _instance = None
+
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super(ModelLoader, cls).__new__(cls)
+            cls._instance._load_models()
+        return cls._instance
+
+    def _load_models(self):
+        print("Initializing models...")
+        self.device = "cuda" if torch.cuda.is_available() else "cpu"
+        print(f"Using device: {self.device}")
+
+        # CNN - Load immediately as it's lightweight
+        print("Loading CNN model...")
+        self.cnn_model = GenderCNN()
+        model_path = "models/gender_model.pth"
+        if os.path.exists(model_path):
+            try:
+                self.cnn_model.load_state_dict(
+                    torch.load(model_path, map_location=torch.device("cpu"))
+                )
+                print("CNN model weights loaded.")
+            except Exception as e:
+                print(f"Error loading CNN weights: {e}. Model will use random initialization or fallback.")
+        self.cnn_model.eval()
+
+        # Initialize pipelines as None - they will be loaded on first use (lazy loading)
+        print("Models initialized with lazy loading strategy.")
+        self._sentiment_pipeline = None
+        self._qa_pipeline = None
+        self._text_gen_pipeline = None
+        self._translator_pipeline = None
+        self._stt_pipeline = None
+        self._zsl_pipeline = None
+        self._gender_classifier = None
+
+    # Lazy loading properties
+    @property
+    def sentiment_pipeline(self):
+        if self._sentiment_pipeline is None:
+            print("Loading Sentiment Analysis model...")
+            self._sentiment_pipeline = self._safe_pipeline(
+                "sentiment-analysis", 
+                model="cardiffnlp/twitter-roberta-base-sentiment-latest"
+            )
+        return self._sentiment_pipeline
+    
+    @property
+    def qa_pipeline(self):
+        if self._qa_pipeline is None:
+            print("Loading QA model...")
+            self._qa_pipeline = self._safe_pipeline(
+                "question-answering", 
+                model="distilbert-base-cased-distilled-squad"
+            )
+        return self._qa_pipeline
+    
+    @property
+    def text_gen_pipeline(self):
+        if self._text_gen_pipeline is None:
+            print("Loading Text Generation model...")
+            self._text_gen_pipeline = self._safe_pipeline(
+                "text-generation", 
+                model="gpt2"
+            )
+        return self._text_gen_pipeline
+    
+    @property
+    def translator_pipeline(self):
+        if self._translator_pipeline is None:
+            print("Loading Translation model...")
+            self._translator_pipeline = self._safe_pipeline(
+                "translation", 
+                model="Helsinki-NLP/opus-mt-en-ur"
+            )
+        return self._translator_pipeline
+    
+    @property
+    def stt_pipeline(self):
+        if self._stt_pipeline is None:
+            print("Loading STT model...")
+            self._stt_pipeline = self._safe_pipeline(
+                "automatic-speech-recognition", 
+                model="openai/whisper-base"
+            )
+        return self._stt_pipeline
+    
+    @property
+    def zsl_pipeline(self):
+        if self._zsl_pipeline is None:
+            print("Loading Zero-Shot Classification model...")
+            self._zsl_pipeline = self._safe_pipeline(
+                "zero-shot-classification", 
+                model="facebook/bart-large-mnli"
+            )
+        return self._zsl_pipeline
+    
+    @property
+    def gender_classifier(self):
+        if self._gender_classifier is None:
+            print("Loading Gender Classifier model...")
+            self._gender_classifier = self._safe_pipeline(
+                "image-classification", 
+                model="prithivMLmods/Gender-Classifier-Mini"
+            )
+        return self._gender_classifier
+
+
+    def _safe_pipeline(self, *args, **kwargs):
+        try:
+            # Explicitly set device (0 for CUDA if available, -1 for CPU)
+            device_idx = 0 if self.device == "cuda" else -1
+            return pipeline(*args, device=device_idx, **kwargs)
+        except Exception as e:
+            print(f"Failed to load pipeline {args} {kwargs}: {e}")
+            return None
+
+# Singleton instance
+loader = ModelLoader()

reproduction_apriori.py

@@ -0,0 +1,59 @@
+import pandas as pd
+from mlxtend.frequent_patterns import apriori, association_rules
+from mlxtend.preprocessing import TransactionEncoder
+import io
+
+def test_apriori(csv_content, min_support=0.1, min_threshold=0.7, metric="lift"):
+    print(f"\n--- Testing with min_support={min_support}, min_threshold={min_threshold}, metric={metric} ---")
+    df = pd.read_csv(io.StringIO(csv_content), header=None)
+    
+    transactions = []
+    values = df.values.tolist()
+    for row in values:
+        transaction = [str(item).strip() for item in row if pd.notna(item) and str(item).strip() != '']
+        if transaction:
+            transactions.append(transaction)
+    
+    print(f"Transactions: {transactions}")
+    
+    te = TransactionEncoder()
+    te_ary = te.fit(transactions).transform(transactions)
+    encoded_df = pd.DataFrame(te_ary, columns=te.columns_)
+    
+    frequent_itemsets = apriori(encoded_df, min_support=min_support, use_colnames=True)
+    if frequent_itemsets.empty:
+        print("No frequent itemsets found.")
+        return
+
+    print(f"Frequent Itemsets:\n{frequent_itemsets}")
+    
+    rules = association_rules(frequent_itemsets, metric=metric, min_threshold=min_threshold)
+    if rules.empty:
+        print("No rules found.")
+        return
+
+    print(f"Rules Found: {len(rules)}")
+    print(rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']])
+
+# Sample data
+data = """Milk,Bread,Eggs
+Milk,Bread
+Milk,Eggs
+Bread,Eggs
+Milk,Bread,Eggs"""
+
+# Test with current app logic (metric="lift")
+test_apriori(data, metric="lift")
+
+# Test with confidence (likely what user wants)
+test_apriori(data, metric="confidence")
+
+# Test with headers (to see if it breaks)
+data_with_header = """Item1,Item2,Item3
+Milk,Bread,Eggs
+Milk,Bread
+Milk,Eggs
+Bread,Eggs
+Milk,Bread,Eggs"""
+print("\n--- Testing with headers ---")
+test_apriori(data_with_header, metric="lift")

reproduction_apriori_v2.py

@@ -0,0 +1,54 @@
+import pandas as pd
+from mlxtend.frequent_patterns import apriori, association_rules
+from mlxtend.preprocessing import TransactionEncoder
+import io
+
+def test_apriori_improved(csv_content, min_support=0.1, min_threshold=0.7, metric="lift", has_header=False):
+    print(f"\n--- Testing: support={min_support}, threshold={min_threshold}, metric={metric}, header={has_header} ---")
+    
+    # Simulate the file reading logic in app.py
+    df = pd.read_csv(io.StringIO(csv_content), header=0 if has_header else None)
+    
+    transactions = []
+    values = df.values.tolist()
+    for row in values:
+        # Improved logic: set, sorted, stripped
+        transaction = sorted(list(set([str(item).strip() for item in row if pd.notna(item) and str(item).strip() != ''])))
+        if transaction:
+            transactions.append(transaction)
+    
+    print(f"Transactions count: {len(transactions)}")
+    
+    te = TransactionEncoder()
+    te_ary = te.fit(transactions).transform(transactions)
+    encoded_df = pd.DataFrame(te_ary, columns=te.columns_)
+    
+    frequent_itemsets = apriori(encoded_df, min_support=min_support, use_colnames=True)
+    if frequent_itemsets.empty:
+        print("No frequent itemsets found.")
+        return
+
+    rules = association_rules(frequent_itemsets, metric=metric, min_threshold=min_threshold)
+    if rules.empty:
+        print("No rules found.")
+        return
+
+    print(f"Rules Found: {len(rules)}")
+    print(rules[['antecedents', 'consequents', 'support', 'confidence', 'lift']].head())
+
+# Sample data with header
+data_with_header = """Item1,Item2,Item3
+Milk,Bread,Eggs
+Milk,Bread
+Milk,Eggs
+Bread,Eggs
+Milk,Bread,Eggs"""
+
+# Test with header=True
+test_apriori_improved(data_with_header, metric="confidence", has_header=True)
+
+# Test with header=False (should see Item1, Item2, Item3 as products in transactions)
+test_apriori_improved(data_with_header, metric="confidence", has_header=False)
+
+# Test with lift
+test_apriori_improved(data_with_header, metric="lift", min_threshold=1.1, has_header=True)

requirements.txt

@@ -0,0 +1,20 @@
+flask
+transformers
+torch
+pillow
+numpy
+gtts
+SpeechRecognition
+sentencepiece
+pandas
+scikit-learn
+matplotlib
+librosa
+mlxtend
+sacremoses
+scipy
+soundfile
+openpyxl
+werkzeug
+openai-whisper
+gunicorn

scripts/setup_env.ps1

@@ -0,0 +1,14 @@
+# PowerShell script to create a venv and install requirements
+# Run in the workspace root: .\scripts\setup_env.ps1
+
+# Create virtual env
+python -m venv .venv
+
+# Activate venv in current session (PowerShell)
+. .venv\Scripts\Activate.ps1
+
+# Upgrade pip and install requirements
+python -m pip install --upgrade pip
+pip install -r requirements.txt
+
+Write-Host "Setup complete. Activate with '. .venv\Scripts\Activate.ps1' and run 'python app.py' to start the server."

static/css/main.css

@@ -0,0 +1,184 @@
+:root {
+    --bg-deep: #05070a;
+    --sidebar-bg: #0a0d14;
+    --card-bg: rgba(16, 20, 28, 0.7);
+    --glass-border: rgba(255, 255, 255, 0.08);
+    --accent-blue: #00d2ff;
+    --accent-purple: #9d50bb;
+    --text-primary: #f0f2f5;
+    --text-secondary: #94a3b8;
+    --quantum-gradient: linear-gradient(135deg, var(--accent-blue), var(--accent-purple));
+    --sidebar-width: 280px;
+    --radius-lg: 16px;
+    --radius-md: 12px;
+    --transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
+}
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+    font-family: 'Outfit', -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
+}
+
+body {
+    background: var(--bg-deep);
+    color: var(--text-primary);
+    overflow-x: hidden;
+    min-height: 100vh;
+}
+
+/* Layout Grid */
+.dashboard-wrapper {
+    display: grid;
+    grid-template-columns: var(--sidebar-width) 1fr;
+    min-height: 100vh;
+}
+
+/* Sidebar Styling */
+.sidebar {
+    background: var(--sidebar-bg);
+    border-right: 1px solid var(--glass-border);
+    padding: 2rem 1.5rem;
+    display: flex;
+    flex-direction: column;
+    gap: 2rem;
+    position: sticky;
+    top: 0;
+    height: 100vh;
+}
+
+.brand {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    padding-left: 0.5rem;
+}
+
+.brand-icon {
+    width: 40px;
+    height: 40px;
+    background: var(--quantum-gradient);
+    border-radius: 10px;
+    display: grid;
+    place-items: center;
+    font-weight: 800;
+    color: white;
+}
+
+.brand-name {
+    font-size: 1.25rem;
+    font-weight: 700;
+    letter-spacing: -0.5px;
+}
+
+.nav-menu {
+    list-style: none;
+    display: flex;
+    flex-direction: column;
+    gap: 0.5rem;
+}
+
+.nav-link {
+    display: flex;
+    align-items: center;
+    gap: 12px;
+    padding: 0.75rem 1rem;
+    color: var(--text-secondary);
+    text-decoration: none;
+    border-radius: var(--radius-md);
+    transition: var(--transition);
+    font-weight: 500;
+}
+
+.nav-link:hover {
+    background: rgba(255, 255, 255, 0.05);
+    color: var(--text-primary);
+}
+
+.nav-link.active {
+    background: rgba(0, 210, 255, 0.1);
+    color: var(--accent-blue);
+}
+
+/* Main Content area */
+.main-content {
+    padding: 2rem;
+    background: radial-gradient(circle at top right, rgba(0, 210, 255, 0.05), transparent 40%);
+}
+
+.top-bar {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 2.5rem;
+}
+
+.page-title h1 {
+    font-size: 2rem;
+    font-weight: 700;
+    margin-bottom: 4px;
+}
+
+.page-title p {
+    color: var(--text-secondary);
+}
+
+/* Reusable Components */
+.glass-card {
+    background: var(--card-bg);
+    backdrop-filter: blur(12px);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-lg);
+    padding: 1.5rem;
+    transition: var(--transition);
+}
+
+.glass-card:hover {
+    border-color: rgba(255, 255, 255, 0.15);
+    transform: translateY(-4px);
+}
+
+.btn-quantum {
+    background: var(--quantum-gradient);
+    color: white;
+    padding: 0.75rem 1.5rem;
+    border: none;
+    border-radius: var(--radius-md);
+    font-weight: 600;
+    cursor: pointer;
+    transition: var(--transition);
+    text-decoration: none;
+    display: inline-flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.btn-quantum:hover {
+    opacity: 0.9;
+    box-shadow: 0 0 20px rgba(0, 210, 255, 0.3);
+}
+
+/* Animations */
+@keyframes fadeIn {
+    from { opacity: 0; transform: translateY(10px); }
+    to { opacity: 1; transform: translateY(0); }
+}
+
+.animate-fade-in {
+    animation: fadeIn 0.5s ease forwards;
+}
+
+/* Responsive */
+@media (max-width: 1024px) {
+    .dashboard-wrapper {
+        grid-template-columns: 80px 1fr;
+    }
+    .brand-name, .nav-text {
+        display: none;
+    }
+    .sidebar {
+        padding: 2rem 1rem;
+        align-items: center;
+    }
+}

static/css/style.css

@@ -0,0 +1,461 @@
+:root {
+    --primary: #6366f1;
+    --primary-hover: #4f46e5;
+    --secondary: #c084fc;
+    --bg-dark: #070b14;
+    --card-bg: rgba(30, 41, 59, 0.4);
+    --text-main: #f8fafc;
+    --text-dim: #94a3b8;
+    --glass-border: rgba(255, 255, 255, 0.08);
+    --glow: rgba(99, 102, 241, 0.15);
+}
+
+* {
+    box-sizing: border-box;
+    margin: 0;
+    padding: 0;
+}
+
+body {
+    font-family: 'Inter', system-ui, -apple-system, sans-serif;
+    background: var(--bg-dark);
+    color: var(--text-main);
+    min-height: 100vh;
+    overflow-x: hidden;
+    background-image:
+        radial-gradient(circle at 20% 20%, rgba(99, 102, 241, 0.1) 0%, transparent 40%),
+        radial-gradient(circle at 80% 80%, rgba(192, 132, 252, 0.1) 0%, transparent 40%);
+}
+
+/* Background animated glow */
+body::before {
+    content: '';
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: url('https://grainy-gradients.vercel.app/noise.svg');
+    opacity: 0.15;
+    pointer-events: none;
+    z-index: 0;
+}
+
+.container {
+    position: relative;
+    z-index: 1;
+    max-width: 1100px;
+    margin: 0 auto;
+    padding: 3rem 1.5rem;
+}
+
+header {
+    text-align: center;
+    padding-bottom: 4rem;
+    animation: fadeInDown 0.8s ease-out;
+}
+
+@keyframes fadeInDown {
+    from {
+        opacity: 0;
+        transform: translateY(-20px);
+    }
+
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+h1 {
+    font-size: clamp(2.5rem, 8vw, 4.5rem);
+    font-weight: 900;
+    letter-spacing: -0.02em;
+    background: linear-gradient(135deg, #818cf8 0%, #c084fc 100%);
+    -webkit-background-clip: text;
+    background-clip: text;
+    -webkit-text-fill-color: transparent;
+    margin-bottom: 1rem;
+    filter: drop-shadow(0 0 10px rgba(129, 140, 248, 0.3));
+}
+
+.subtitle {
+    color: var(--text-dim);
+    font-size: 1.25rem;
+    max-width: 600px;
+    margin: 0 auto;
+    line-height: 1.6;
+}
+
+/* Grid Layout */
+.grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
+    gap: 2rem;
+    margin-top: 2rem;
+}
+
+.card {
+    background: var(--card-bg);
+    backdrop-filter: blur(16px);
+    -webkit-backdrop-filter: blur(16px);
+    border: 1px solid var(--glass-border);
+    border-radius: 2rem;
+    padding: 2.5rem;
+    transition: all 0.4s cubic-bezier(0.23, 1, 0.32, 1);
+    text-decoration: none;
+    color: inherit;
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    text-align: center;
+    position: relative;
+    overflow: hidden;
+}
+
+.card::after {
+    content: '';
+    position: absolute;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: linear-gradient(135deg, rgba(255, 255, 255, 0.05) 0%, transparent 100%);
+    pointer-events: none;
+}
+
+.card:hover {
+    transform: translateY(-12px) scale(1.02);
+    border-color: rgba(99, 102, 241, 0.3);
+    box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.5), 0 0 20px var(--glow);
+    background: rgba(30, 41, 59, 0.6);
+}
+
+.card i {
+    font-size: 3rem;
+    margin-bottom: 1.5rem;
+    background: linear-gradient(135deg, #6366f1, #a855f7);
+    -webkit-background-clip: text;
+    background-clip: text;
+    -webkit-text-fill-color: transparent;
+    transition: transform 0.3s ease;
+}
+
+.card:hover i {
+    transform: scale(1.1) rotate(5deg);
+}
+
+.card h3 {
+    margin-bottom: 0.75rem;
+    font-size: 1.75rem;
+    font-weight: 700;
+}
+
+.card p {
+    color: var(--text-dim);
+    font-size: 1rem;
+    line-height: 1.6;
+}
+
+/* Form Styles */
+.form-card {
+    background: var(--card-bg);
+    backdrop-filter: blur(20px);
+    border: 1px solid var(--glass-border);
+    border-radius: 2.5rem;
+    padding: 3rem;
+    max-width: 700px;
+    margin: 3rem auto;
+    box-shadow: 0 40px 100px -20px rgba(0, 0, 0, 0.4);
+}
+
+.form-group {
+    margin-bottom: 2rem;
+}
+
+label {
+    display: block;
+    margin-bottom: 0.75rem;
+    font-weight: 600;
+    color: var(--text-main);
+    font-size: 1rem;
+}
+
+textarea,
+input[type="text"],
+input[type="file"] {
+    width: 100%;
+    background: rgba(15, 23, 42, 0.6);
+    border: 1px solid var(--glass-border);
+    border-radius: 1rem;
+    padding: 1.25rem;
+    color: white;
+    font-family: inherit;
+    font-size: 1rem;
+    transition: all 0.3s;
+}
+
+textarea:focus,
+input[type="text"]:focus {
+    outline: none;
+    border-color: var(--primary);
+    background: rgba(15, 23, 42, 0.8);
+    box-shadow: 0 0 0 4px rgba(99, 102, 241, 0.1);
+}
+
+button {
+    background: linear-gradient(135deg, var(--primary) 0%, var(--secondary) 100%);
+    color: white;
+    border: none;
+    padding: 1.25rem 2rem;
+    border-radius: 1rem;
+    font-weight: 700;
+    font-size: 1.1rem;
+    cursor: pointer;
+    transition: all 0.3s;
+    width: 100%;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    gap: 0.75rem;
+    box-shadow: 0 10px 15px -3px rgba(99, 102, 241, 0.3);
+}
+
+button:hover {
+    transform: translateY(-2px);
+    box-shadow: 0 20px 25px -5px rgba(99, 102, 241, 0.4);
+    filter: brightness(1.1);
+}
+
+button:active {
+    transform: translateY(0);
+}
+
+/* Results Section */
+.result-box {
+    margin-top: 3rem;
+    padding: 2.5rem;
+    background: linear-gradient(135deg, rgba(99, 102, 241, 0.1), rgba(192, 132, 252, 0.1));
+    border: 1px solid rgba(99, 102, 241, 0.2);
+    border-radius: 1.5rem;
+    animation: slideUp 0.5s ease-out;
+}
+
+@keyframes slideUp {
+    from {
+        opacity: 0;
+        transform: translateY(20px);
+    }
+
+    to {
+        opacity: 1;
+        transform: translateY(0);
+    }
+}
+
+.back-link {
+    display: inline-flex;
+    align-items: center;
+    gap: 0.5rem;
+    margin-bottom: 2rem;
+    color: var(--text-dim);
+    text-decoration: none;
+    font-weight: 500;
+    transition: color 0.2s;
+}
+
+.back-link:hover {
+    color: var(--text-main);
+}
+
+/* Voice Recorder UI */
+.recorder-container {
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    gap: 1.5rem;
+    margin-bottom: 2rem;
+}
+
+.record-btn {
+    width: 80px;
+    height: 80px;
+    border-radius: 50%;
+    background: #ef4444;
+    border: 6px solid rgba(239, 68, 68, 0.2);
+    color: white;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    cursor: pointer;
+    transition: all 0.3s;
+    font-size: 1.5rem;
+}
+
+.record-btn.recording {
+    animation: pulse 1.5s infinite;
+    background: #dc2626;
+    border-radius: 1rem;
+}
+
+@keyframes pulse {
+    0% {
+        transform: scale(1);
+        box-shadow: 0 0 0 0 rgba(239, 68, 68, 0.7);
+    }
+
+    70% {
+        transform: scale(1.05);
+        box-shadow: 0 0 0 20px rgba(239, 68, 68, 0);
+    }
+
+    100% {
+        transform: scale(1);
+        box-shadow: 0 0 0 0 rgba(239, 68, 68, 0);
+    }
+}
+
+/* Loading Overlay */
+#loading-overlay {
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
+    height: 100%;
+    background: rgba(7, 11, 20, 0.8);
+    backdrop-filter: blur(8px);
+    display: none;
+    flex-direction: column;
+    align-items: center;
+    justify-content: center;
+    z-index: 1000;
+}
+
+.loader {
+    width: 60px;
+    height: 60px;
+    border: 5px solid rgba(99, 102, 241, 0.1);
+    border-top: 5px solid var(--primary);
+    border-radius: 50%;
+    animation: spin 1s linear infinite;
+    margin-bottom: 1.5rem;
+}
+
+@keyframes spin {
+    0% {
+        transform: rotate(0deg);
+    }
+
+    100% {
+        transform: rotate(360deg);
+    }
+}
+
+/* Image Preview */
+#preview-container {
+    width: 100%;
+    height: 300px;
+    border-radius: 1.5rem;
+    overflow: hidden;
+    margin-bottom: 1.5rem;
+    display: none;
+    border: 2px dashed var(--glass-border);
+}
+
+#preview-img {
+    width: 100%;
+    height: 100%;
+    object-fit: cover;
+}
+
+/* Confidence Meter */
+.confidence-container {
+    margin-top: 1.5rem;
+    text-align: left;
+}
+
+.confidence-bar {
+    background: rgba(15, 23, 42, 0.4);
+    border-radius: 1rem;
+    height: 12px;
+    width: 100%;
+    overflow: hidden;
+    margin: 0.5rem 0;
+}
+
+.confidence-fill {
+    background: linear-gradient(90deg, var(--primary), var(--secondary));
+    height: 100%;
+    transition: width 1s cubic-bezier(0.34, 1.56, 0.64, 1);
+}
+
+/* Copy Button */
+.copy-btn {
+    background: rgba(255, 255, 255, 0.05);
+    border: 1px solid var(--glass-border);
+    color: var(--text-dim);
+    padding: 0.5rem 1rem;
+    border-radius: 0.75rem;
+    font-size: 0.875rem;
+    cursor: pointer;
+    display: inline-flex;
+    align-items: center;
+    gap: 0.5rem;
+    transition: all 0.2s;
+    margin-bottom: 1rem;
+    width: auto;
+}
+
+.copy-btn:hover {
+    background: rgba(255, 255, 255, 0.1);
+    color: var(--text-main);
+}
+
+/* Range Slider */
+.slider-container {
+    margin-bottom: 2rem;
+}
+
+input[type="range"] {
+    -webkit-appearance: none;
+    width: 100%;
+    height: 6px;
+    background: rgba(15, 23, 42, 0.6);
+    border-radius: 5px;
+    outline: none;
+    margin: 1rem 0;
+}
+
+input[type="range"]::-webkit-slider-thumb {
+    -webkit-appearance: none;
+    appearance: none;
+    width: 20px;
+    height: 20px;
+    background: var(--primary);
+    border-radius: 50%;
+    cursor: pointer;
+    box-shadow: 0 0 10px rgba(99, 102, 241, 0.5);
+}
+
+/* Floating Actions */
+.floating-actions {
+    display: flex;
+    justify-content: flex-end;
+    gap: 0.5rem;
+}
+
+/* Responsive */
+@media (max-width: 640px) {
+    .container {
+        padding: 1.5rem;
+    }
+
+    .form-card {
+        padding: 1.5rem;
+        border-radius: 1.5rem;
+    }
+
+    h1 {
+        font-size: 2.5rem;
+    }
+}

static/style.css

@@ -0,0 +1,192 @@
+/* Google Fonts */
+@import url('https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;600&display=swap');
+
+:root {
+    --bg-color: #0f172a;
+    --card-bg: #1e293b;
+    --text-color: #f1f5f9;
+    --accent-color: #3b82f6;
+    --accent-hover: #2563eb;
+    --gradient-1: linear-gradient(135deg, #3b82f6 0%, #8b5cf6 100%);
+    --glass-bg: rgba(30, 41, 59, 0.7);
+    --border-color: rgba(255, 255, 255, 0.1);
+    --container-max: 960px;
+}
+
+* {
+    margin: 0;
+    padding: 0;
+    box-sizing: border-box;
+    font-family: 'Outfit', sans-serif;
+}
+
+body {
+    background-color: var(--bg-color);
+    color: var(--text-color);
+    min-height: 100vh;
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    padding: 2rem;
+}
+
+h1 {
+    font-size: 2rem;
+    font-weight: 600;
+    margin-bottom: 2rem;
+    text-align: center;
+    background: var(--gradient-1);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+}
+
+.container {
+    width: 100%;
+    max-width: var(--container-max);
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(300px, 1fr));
+    gap: 2rem;
+}
+
+/* Service Cards (Index) */
+.card {
+    background: var(--card-bg);
+    padding: 2rem;
+    border-radius: 1rem;
+    border: 1px solid var(--border-color);
+    transition: transform 0.3s ease, box-shadow 0.3s ease;
+    text-decoration: none;
+    color: inherit;
+    display: flex;
+    flex-direction: column;
+    align-items: center;
+    justify-content: center;
+    text-align: center;
+}
+
+.card:hover {
+    transform: translateY(-5px);
+    box-shadow: 0 10px 20px rgba(0, 0, 0, 0.3);
+    border-color: var(--accent-color);
+}
+
+.card h2 {
+    font-size: 1.5rem;
+    margin-bottom: 0.5rem;
+}
+
+.card p {
+    color: #94a3b8;
+    font-size: 0.9rem;
+}
+
+/* Forms & Service Pages */
+.service-container {
+    background: var(--card-bg);
+    padding: 3rem;
+    border-radius: 1rem;
+    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1);
+    width: 100%;
+    max-width: 600px;
+    border: 1px solid var(--border-color);
+}
+
+.service-title {
+    margin-bottom: 1.5rem;
+    text-align: center;
+}
+
+label {
+    display: block;
+    margin-bottom: 0.5rem;
+    color: #cbd5e1;
+}
+
+input[type="text"],
+input[type="file"],
+textarea {
+    width: 100%;
+    padding: 0.75rem;
+    margin-bottom: 1.5rem;
+    background: var(--bg-color);
+    border: 1px solid var(--border-color);
+    border-radius: 0.5rem;
+    color: var(--text-color);
+    font-size: 1rem;
+}
+
+input[type="file"]::file-selector-button {
+    background: var(--card-bg);
+    color: var(--text-color);
+    padding: 0.5rem 1rem;
+    border: 1px solid var(--border-color);
+    border-radius: 0.3rem;
+    cursor: pointer;
+    margin-right: 1rem;
+}
+
+button {
+    width: 100%;
+    padding: 0.6rem;
+    background: var(--gradient-1);
+    color: white;
+    border: none;
+    border-radius: 0.5rem;
+    font-size: 0.98rem;
+    font-weight: 600;
+    cursor: pointer;
+    transition: filter 0.18s ease;
+}
+
+button:hover {
+    filter: brightness(1.1);
+}
+
+.result-box {
+    margin-top: 2rem;
+    padding: 1rem;
+    background: rgba(59, 130, 246, 0.06);
+    border: 1px solid rgba(59,130,246,0.12);
+    border-radius: 0.5rem;
+    text-align: center;
+}
+
+.back-link {
+    display: block;
+    margin-top: 1.5rem;
+    text-align: center;
+    color: var(--accent-color);
+    text-decoration: none;
+}
+
+.back-link:hover {
+    text-decoration: underline;
+}
+
+audio {
+    width: 100%;
+    margin-top: 10px;
+}
+
+/* Make images responsive and add subtle rounding */
+img {
+    max-width: 100%;
+    height: auto;
+    display: block;
+    border-radius: 0.5rem;
+}
+
+/* Improve focus styles for accessibility */
+input[type="text"],
+input[type="file"],
+textarea {
+    transition: box-shadow 0.15s ease, border-color 0.15s ease;
+}
+
+input[type="text"]:focus,
+input[type="file"]:focus,
+textarea:focus {
+    outline: none;
+    box-shadow: 0 0 0 4px rgba(59,130,246,0.08);
+    border-color: var(--accent-color);
+}

templates/apriori.html

@@ -0,0 +1,209 @@
+{% extends "layout.html" %}
+
+{% block title %}Association Rules - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Association Rules</h1>
+<p>Discover hidden relationships in transactional datasets using the A-priori algorithm.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+    <form action="/apriori" method="post" enctype="multipart/form-data" class="quantum-form">
+        <div class="upload-zone" id="dropZone">
+            <i class="fas fa-shopping-cart upload-icon"></i>
+            <div class="upload-text">
+                <strong>Upload Transaction Data</strong>
+                <span>Supports .CSV or .XLSX (Each row is a transaction)</span>
+            </div>
+            <input type="file" name="file" accept=".csv, .xlsx" required>
+        </div>
+
+        <div class="settings-grid">
+            <div class="input-group">
+                <label>Metric</label>
+                <select name="metric" class="quantum-select">
+                    <option value="lift" selected>Lift</option>
+                    <option value="confidence">Confidence</option>
+                </select>
+            </div>
+            <div class="input-group">
+                <label>Min Support</label>
+                <input type="number" name="min_support" value="0.1" min="0.01" max="1" step="0.01" required>
+            </div>
+            <div class="input-group">
+                <label>Min Threshold (Confidence/Lift)</label>
+                <input type="number" name="min_threshold" value="0.7" min="0.1" max="10" step="0.1" required>
+            </div>
+            <div class="input-group checkbox-group">
+                <label class="checkbox-container">
+                    <input type="checkbox" name="has_header">
+                    <span class="checkmark"></span>
+                    File has header row
+                </label>
+            </div>
+        </div>
+
+        <button type="submit" class="btn-quantum full-width">
+            <i class="fas fa-magic"></i> Generate Rules
+        </button>
+    </form>
+
+    {% if error %}
+    <div class="error-msg animate-fade-in">
+        <i class="fas fa-exclamation-triangle"></i> {{ error }}
+    </div>
+    {% endif %}
+
+    {% if rules %}
+    <div class="result-container animate-fade-in">
+        <div class="result-header">Mining Results: {{ rules|length }} rules discovered</div>
+
+        <div class="table-container">
+            <table class="quantum-table">
+                <thead>
+                    <tr>
+                        <th>Antecedents (If)</th>
+                        <th>Consequents (Then)</th>
+                        <th>Support</th>
+                        <th>Confidence</th>
+                        <th>Lift</th>
+                    </tr>
+                </thead>
+                <tbody>
+                    {% for rule in rules %}
+                    <tr>
+                        <td><span class="tag">{{ rule.antecedents | join(', ') }}</span></td>
+                        <td><span class="tag consequent">{{ rule.consequents | join(', ') }}</span></td>
+                        <td>{{ "%.4f"|format(rule.support) }}</td>
+                        <td>{{ "%.4f"|format(rule.confidence) }}</td>
+                        <td>{{ "%.4f"|format(rule.lift) }}</td>
+                    </tr>
+                    {% endfor %}
+                </tbody>
+            </table>
+        </div>
+    </div>
+    {% endif %}
+</div>
+
+<style>
+    .service-panel {
+        max-width: 1000px;
+        margin: 0 auto;
+    }
+
+    .settings-grid {
+        display: grid;
+        grid-template-columns: 1fr 1fr;
+        gap: 1.5rem;
+        margin-top: 1.5rem;
+    }
+
+    .input-group label {
+        font-size: 0.85rem;
+        font-weight: 700;
+        color: var(--text-secondary);
+        text-transform: uppercase;
+        margin-bottom: 0.5rem;
+        display: block;
+    }
+
+    input[type="number"] {
+        background: rgba(0, 0, 0, 0.2);
+        border: 1px solid var(--glass-border);
+        border-radius: var(--radius-md);
+        padding: 0.75rem 1rem;
+        color: var(--text-primary);
+        font-size: 1rem;
+        width: 100%;
+    }
+
+    .table-container {
+        margin-top: 1.5rem;
+        overflow-x: auto;
+        background: rgba(0, 0, 0, 0.2);
+        border-radius: var(--radius-lg);
+        border: 1px solid var(--glass-border);
+    }
+
+    .quantum-table {
+        width: 100%;
+        border-collapse: collapse;
+        text-align: left;
+    }
+
+    .quantum-table th {
+        padding: 1rem;
+        background: rgba(255, 255, 255, 0.05);
+        color: var(--text-secondary);
+        font-size: 0.8rem;
+        text-transform: uppercase;
+        letter-spacing: 1px;
+    }
+
+    .quantum-table td {
+        padding: 1rem;
+        border-top: 1px solid var(--glass-border);
+        font-size: 0.9rem;
+    }
+
+    .tag {
+        background: rgba(59, 130, 246, 0.2);
+        color: #60a5fa;
+        padding: 2px 8px;
+        border-radius: 4px;
+        font-size: 0.8rem;
+        font-weight: 600;
+    }
+
+    .tag.consequent {
+        background: rgba(168, 85, 247, 0.2);
+        color: #c084fc;
+    }
+
+    .quantum-select {
+        background: rgba(0, 0, 0, 0.2);
+        border: 1px solid var(--glass-border);
+        border-radius: var(--radius-md);
+        padding: 0.75rem 1rem;
+        color: var(--text-primary);
+        font-size: 1rem;
+        width: 100%;
+        cursor: pointer;
+    }
+
+    .quantum-select option {
+        background: #1a1a2e;
+        color: white;
+    }
+
+    .checkbox-group {
+        display: flex;
+        align-items: flex-end;
+    }
+
+    .checkbox-container {
+        display: flex;
+        align-items: center;
+        cursor: pointer;
+        font-size: 0.9rem;
+        color: var(--text-secondary);
+        user-select: none;
+    }
+
+    .checkbox-container input {
+        margin-right: 10px;
+        width: 18px;
+        height: 18px;
+    }
+
+    .error-msg {
+        background: rgba(239, 68, 68, 0.1);
+        color: #ef4444;
+        padding: 1rem;
+        border-radius: var(--radius-md);
+        margin: 1rem 0;
+    }
+</style>
+{% endblock %}

templates/clustering.html

@@ -0,0 +1,185 @@
+{% extends "layout.html" %}
+
+{% block title %}Data Clusters - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Data Clusters</h1>
+<p>Unsupervised grouping of multivariate datasets using K-Means.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+    <form action="/clustering" method="post" enctype="multipart/form-data" class="quantum-form">
+        <div class="upload-zone" id="dropZone">
+            <i class="fas fa-file-csv upload-icon"></i>
+            <div class="upload-text">
+                <strong>Upload Data Structure</strong>
+                <span>Supports .CSV or .XLSX datasets</span>
+            </div>
+            <input type="file" name="file" accept=".csv, .xlsx" required onchange="handleFile(this)">
+        </div>
+
+        <div class="cluster-settings">
+            <div class="input-group">
+                <label>Cluster Centroids (K)</label>
+                <input type="number" name="clusters" value="3" min="2" max="10" required>
+            </div>
+        </div>
+
+        <button type="submit" class="btn-quantum full-width">
+            <i class="fas fa-chart-pie"></i> Map Clusters
+        </button>
+    </form>
+
+    {% if error %}
+    <div class="error-msg animate-fade-in">
+        <i class="fas fa-exclamation-triangle"></i> {{ error }}
+    </div>
+    {% endif %}
+
+    {% if plot_url %}
+    <div class="result-container animate-fade-in">
+        <div class="result-header">Clustering Schema Visualization</div>
+
+        <div class="visualization-box">
+            <img src="data:image/png;base64,{{ plot_url }}" alt="Clustering Plot">
+        </div>
+
+        {% if cluster_info %}
+        <div class="cluster-stats">
+            <label>Population Distribution</label>
+            <div class="stats-grid">
+                {% for cluster, count in cluster_info.items() %}
+                <div class="stat-card">
+                    <span class="cluster-id">Cluster {{ cluster }}</span>
+                    <span class="count-value">{{ count }} Entities</span>
+                </div>
+                {% endfor %}
+            </div>
+        </div>
+        {% endif %}
+    </div>
+    {% endif %}
+</div>
+
+<style>
+    .service-panel {
+        max-width: 900px;
+        margin: 0 auto;
+    }
+
+    .upload-zone {
+        border: 2px dashed var(--glass-border);
+        border-radius: var(--radius-lg);
+        padding: 3rem;
+        text-align: center;
+        position: relative;
+        background: rgba(0, 0, 0, 0.1);
+    }
+
+    .upload-zone input {
+        position: absolute;
+        inset: 0;
+        opacity: 0;
+        cursor: pointer;
+    }
+
+    .upload-icon {
+        font-size: 3rem;
+        color: var(--accent-blue);
+        margin-bottom: 1rem;
+    }
+
+    .cluster-settings {
+        margin-top: 1.5rem;
+    }
+
+    .input-group label {
+        font-size: 0.85rem;
+        font-weight: 700;
+        color: var(--text-secondary);
+        text-transform: uppercase;
+        margin-bottom: 0.5rem;
+        display: block;
+    }
+
+    input[type="number"] {
+        background: rgba(0, 0, 0, 0.2);
+        border: 1px solid var(--glass-border);
+        border-radius: var(--radius-md);
+        padding: 0.75rem 1rem;
+        color: var(--text-primary);
+        font-size: 1.1rem;
+        width: 100px;
+    }
+
+    .visualization-box {
+        background: white;
+        /* Contrast for charts */
+        padding: 1.5rem;
+        border-radius: var(--radius-lg);
+        margin-top: 1rem;
+        display: flex;
+        justify-content: center;
+        overflow: hidden;
+    }
+
+    .visualization-box img {
+        max-width: 100%;
+        height: auto;
+    }
+
+    .cluster-stats {
+        margin-top: 2rem;
+    }
+
+    .cluster-stats label {
+        color: var(--text-secondary);
+        font-weight: 600;
+        display: block;
+        margin-bottom: 1rem;
+    }
+
+    .stats-grid {
+        display: grid;
+        grid-template-columns: repeat(auto-fill, minmax(180px, 1fr));
+        gap: 1rem;
+    }
+
+    .stat-card {
+        background: rgba(255, 255, 255, 0.03);
+        padding: 1.25rem;
+        border-radius: var(--radius-md);
+        display: flex;
+        flex-direction: column;
+        border-left: 3px solid var(--accent-purple);
+    }
+
+    .cluster-id {
+        font-size: 0.8rem;
+        font-weight: 700;
+        color: var(--accent-purple);
+        text-transform: uppercase;
+        margin-bottom: 4px;
+    }
+
+    .count-value {
+        font-size: 1.2rem;
+        font-weight: 800;
+    }
+
+    .error-msg {
+        background: rgba(239, 68, 68, 0.1);
+        color: #ef4444;
+        padding: 1rem;
+        border-radius: var(--radius-md);
+        margin: 1rem 0;
+    }
+</style>
+
+<script>
+    function handleFile(input) {
+        // Simple visual feedback could go here
+    }
+</script>
+{% endblock %}

templates/dbscan.html

@@ -0,0 +1,168 @@
+{% extends "layout.html" %}
+
+{% block title %}DBSCAN Clusters - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>DBSCAN Clusters</h1>
+<p>Density-Based Spatial Clustering of Applications with Noise (DBSCAN).</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+    <form action="/dbscan" method="post" enctype="multipart/form-data" class="quantum-form">
+        <div class="upload-zone" id="dropZone">
+            <i class="fas fa-braille upload-icon"></i>
+            <div class="upload-text">
+                <strong>Upload Data Structure</strong>
+                <span>Supports .CSV or .XLSX datasets</span>
+            </div>
+            <input type="file" name="file" accept=".csv, .xlsx" required>
+        </div>
+
+        <div class="settings-grid">
+            <div class="input-group">
+                <label>Epsilon (eps)</label>
+                <input type="number" name="eps" value="0.5" min="0.01" max="10" step="0.01" required>
+            </div>
+            <div class="input-group">
+                <label>Min Samples</label>
+                <input type="number" name="min_samples" value="5" min="1" max="100" required>
+            </div>
+        </div>
+
+        <button type="submit" class="btn-quantum full-width">
+            <i class="fas fa-project-diagram"></i> Analyze Density
+        </button>
+    </form>
+
+    {% if error %}
+    <div class="error-msg animate-fade-in">
+        <i class="fas fa-exclamation-triangle"></i> {{ error }}
+    </div>
+    {% endif %}
+
+    {% if plot_url %}
+    <div class="result-container animate-fade-in">
+        <div class="result-header">Density Map Visualization</div>
+
+        <div class="visualization-box">
+            <img src="data:image/png;base64,{{ plot_url }}" alt="DBSCAN Plot">
+        </div>
+
+        {% if cluster_info %}
+        <div class="cluster-stats">
+            <label>Density Distribution (-1 denotes noise)</label>
+            <div class="stats-grid">
+                {% for cluster, count in cluster_info.items() %}
+                <div class="stat-card {% if cluster|int == -1 %}noise-card{% endif %}">
+                    <span class="cluster-id">{% if cluster|int == -1 %}Noise (Outliers){% else %}Cluster {{ cluster }}{%
+                        endif %}</span>
+                    <span class="count-value">{{ count }} Entities</span>
+                </div>
+                {% endfor %}
+            </div>
+        </div>
+        {% endif %}
+    </div>
+    {% endif %}
+</div>
+
+<style>
+    .service-panel {
+        max-width: 900px;
+        margin: 0 auto;
+    }
+
+    .settings-grid {
+        display: grid;
+        grid-template-columns: 1fr 1fr;
+        gap: 1.5rem;
+        margin-top: 1.5rem;
+    }
+
+    .input-group label {
+        font-size: 0.85rem;
+        font-weight: 700;
+        color: var(--text-secondary);
+        text-transform: uppercase;
+        margin-bottom: 0.5rem;
+        display: block;
+    }
+
+    input[type="number"] {
+        background: rgba(0, 0, 0, 0.2);
+        border: 1px solid var(--glass-border);
+        border-radius: var(--radius-md);
+        padding: 0.75rem 1rem;
+        color: var(--text-primary);
+        font-size: 1.1rem;
+        width: 100%;
+    }
+
+    .visualization-box {
+        background: white;
+        padding: 1.5rem;
+        border-radius: var(--radius-lg);
+        margin-top: 1rem;
+        display: flex;
+        justify-content: center;
+        overflow: hidden;
+    }
+
+    .visualization-box img {
+        max-width: 100%;
+        height: auto;
+    }
+
+    .cluster-stats {
+        margin-top: 2rem;
+    }
+
+    .cluster-stats label {
+        color: var(--text-secondary);
+        font-weight: 600;
+        display: block;
+        margin-bottom: 1rem;
+    }
+
+    .stats-grid {
+        display: grid;
+        grid-template-columns: repeat(auto-fill, minmax(180px, 1fr));
+        gap: 1rem;
+    }
+
+    .stat-card {
+        background: rgba(255, 255, 255, 0.03);
+        padding: 1.25rem;
+        border-radius: var(--radius-md);
+        display: flex;
+        flex-direction: column;
+        border-left: 3px solid var(--accent-blue);
+    }
+
+    .stat-card.noise-card {
+        border-left-color: #ef4444;
+    }
+
+    .cluster-id {
+        font-size: 0.8rem;
+        font-weight: 700;
+        color: var(--text-secondary);
+        text-transform: uppercase;
+        margin-bottom: 4px;
+    }
+
+    .count-value {
+        font-size: 1.2rem;
+        font-weight: 800;
+    }
+
+    .error-msg {
+        background: rgba(239, 68, 68, 0.1);
+        color: #ef4444;
+        padding: 1rem;
+        border-radius: var(--radius-md);
+        margin: 1rem 0;
+    }
+</style>
+{% endblock %}

templates/gender.html

@@ -0,0 +1,175 @@
+{% extends "layout.html" %}
+
+{% block title %}Gender Discovery - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Gender Discovery</h1>
+<p>Upload a visual specimen for neural gender classification.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+  <form action="/gender" method="post" enctype="multipart/form-data" class="quantum-form">
+    <div class="upload-zone" id="dropZone">
+      <i class="fas fa-cloud-upload-alt upload-icon"></i>
+      <div class="upload-text">
+        <strong>Click to upload</strong> or drag and drop
+        <span>PNG, JPG or WEBP (max. 10MB)</span>
+      </div>
+      <input type="file" name="image" id="fileInput" accept="image/*" required onchange="handleFile(this)">
+    </div>
+
+    <div id="filePreview" class="file-preview"></div>
+
+    <button type="submit" class="btn-quantum full-width">
+      <i class="fas fa-microchip"></i> Run Discovery Engine
+    </button>
+  </form>
+
+  {% if result %}
+  <div class="result-container animate-fade-in">
+    <div class="result-header">Engine Output</div>
+    <div class="result-display">
+      <span class="label">Detected Gender</span>
+      <span class="value">{{ result }}</span>
+    </div>
+    <div class="result-note">
+      <i class="fas fa-info-circle"></i> The vision model identifies facial features to determine classification.
+    </div>
+  </div>
+  {% endif %}
+</div>
+
+<style>
+  .service-panel {
+    max-width: 700px;
+    margin: 0 auto;
+  }
+
+  .quantum-form {
+    display: flex;
+    flex-direction: column;
+    gap: 1.5rem;
+  }
+
+  .upload-zone {
+    border: 2px dashed var(--glass-border);
+    border-radius: var(--radius-lg);
+    padding: 3rem 2rem;
+    text-align: center;
+    cursor: pointer;
+    transition: var(--transition);
+    position: relative;
+  }
+
+  .upload-zone:hover,
+  .upload-zone.dragover {
+    border-color: var(--accent-blue);
+    background: rgba(0, 210, 255, 0.05);
+  }
+
+  .upload-icon {
+    font-size: 3rem;
+    color: var(--accent-blue);
+    margin-bottom: 1rem;
+  }
+
+  .upload-text {
+    color: var(--text-secondary);
+    display: flex;
+    flex-direction: column;
+    gap: 4px;
+  }
+
+  .upload-text strong {
+    color: var(--text-primary);
+  }
+
+  #fileInput {
+    position: absolute;
+    inset: 0;
+    opacity: 0;
+    cursor: pointer;
+  }
+
+  .full-width {
+    width: 100%;
+    justify-content: center;
+    padding: 1rem;
+    font-size: 1.1rem;
+  }
+
+  .file-preview {
+    margin-top: 0.5rem;
+    color: var(--accent-blue);
+    font-weight: 500;
+    text-align: center;
+  }
+
+  .result-container {
+    margin-top: 2rem;
+    padding-top: 2rem;
+    border-top: 1px solid var(--glass-border);
+  }
+
+  .result-header {
+    text-transform: uppercase;
+    letter-spacing: 2px;
+    font-size: 0.75rem;
+    font-weight: 800;
+    color: var(--accent-purple);
+    margin-bottom: 1rem;
+  }
+
+  .result-display {
+    background: rgba(255, 255, 255, 0.03);
+    padding: 1.5rem;
+    border-radius: var(--radius-md);
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+  }
+
+  .result-display .label {
+    font-size: 1.1rem;
+    color: var(--text-secondary);
+  }
+
+  .result-display .value {
+    font-size: 2rem;
+    font-weight: 800;
+    color: var(--text-primary);
+    text-transform: capitalize;
+  }
+
+  .result-note {
+    margin-top: 1rem;
+    font-size: 0.85rem;
+    color: var(--text-secondary);
+    font-style: italic;
+  }
+</style>
+
+<script>
+  function handleFile(input) {
+    const preview = document.getElementById('filePreview');
+    if (input.files && input.files[0]) {
+      preview.innerHTML = `<i class="fas fa-file-image"></i> Selected: ${input.files[0].name}`;
+    }
+  }
+
+  const dropZone = document.getElementById('dropZone');
+  ['dragenter', 'dragover'].forEach(name => {
+    dropZone.addEventListener(name, (e) => {
+      e.preventDefault();
+      dropZone.classList.add('dragover');
+    });
+  });
+  ['dragleave', 'drop'].forEach(name => {
+    dropZone.addEventListener(name, (e) => {
+      e.preventDefault();
+      dropZone.classList.remove('dragover');
+    });
+  });
+</script>
+{% endblock %}

templates/generate.html

@@ -0,0 +1,69 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Muse Text Gen - AI Magic Hub</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">
+</head>
+
+<body>
+    <div id="loading-overlay">
+        <div class="loader"></div>
+        <p>Awakening the Muse...</p>
+    </div>
+
+    <div class="container">
+        <a href="/" class="back-link"><i class="fas fa-arrow-left"></i> Back to Dashboard</a>
+        <header>
+            <h1>Muse Text Gen</h1>
+            <p class="subtitle">Powered by GPT-2. Enter a prompt and watch the AI weave a narrative beyond imagination.
+            </p>
+        </header>
+
+        <div class="form-card">
+            <form id="generate-form" method="POST">
+                <div class="form-group">
+                    <label for="prompt">Story Prompt</label>
+                    <textarea name="prompt" id="prompt" rows="4" required
+                        placeholder="Once upon a time in a digital realm...">{{ prompt if prompt else '' }}</textarea>
+                </div>
+
+                <div class="slider-container">
+                    <label for="temperature">Creativity Level: <span id="temp-val">{{ temperature }}</span></label>
+                    <input type="range" name="temperature" id="temperature" min="0.1" max="1.5" step="0.1"
+                        value="{{ temperature }}">
+                    <p style="font-size: 0.75rem; color: var(--text-dim); margin-top: 0.5rem;">Higher values produce
+                        more creative but less predictable text.</p>
+                </div>
+
+                <button type="submit"><i class="fas fa-sparkles"></i> Conjure Story</button>
+            </form>
+
+            {% if result %}
+            <div class="result-box">
+                <div class="floating-actions">
+                    <button class="copy-btn" onclick="copyToClipboard('generated-text')">
+                        <i class="fas fa-copy"></i> Copy
+                    </button>
+                </div>
+                <p style="font-size: 0.875rem; color: var(--text-dim); margin-bottom: 1rem;">Generated Text:</p>
+                <div id="generated-text" style="line-height: 1.8; color: var(--text-main);">
+                    {{ result }}
+                </div>
+            </div>
+            {% endif %}
+        </div>
+    </div>
+
+    <script>
+        document.getElementById('gen-form').onsubmit = () => {
+            document.getElementById('loading-overlay').style.display = 'flex';
+        };
+    </script>
+</body>
+
+</html>

templates/image.html

@@ -0,0 +1,95 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Gender Vision - AI Magic Hub</title>
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/style.css') }}">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <link href="https://fonts.googleapis.com/css2?family=Inter:wght@400;600;700;900&display=swap" rel="stylesheet">
+</head>
+
+<body>
+    <div id="loading-overlay">
+        <div class="loader"></div>
+        <p>Analyzing Image...</p>
+    </div>
+
+    <div class="container">
+        <a href="/" class="back-link"><i class="fas fa-arrow-left"></i> Back to Dashboard</a>
+        <header>
+            <h1>Gender Vision</h1>
+            <p class="subtitle">Upload a portrait to identify gender using our advanced CNN model.</p>
+        </header>
+
+        <div class="form-card">
+            <div id="preview-container"
+                style="display: none; width: 100%; height: 300px; border-radius: 1.5rem; overflow: hidden; margin-bottom: 2rem; border: 2px dashed var(--glass-border);">
+                <img id="preview-img" src="" alt="Preview" style="width: 100%; height: 100%; object-fit: cover;">
+            </div>
+
+            <form id="upload-form" method="POST" enctype="multipart/form-data">
+                <div class="form-group">
+                    <label for="file">Select Image</label>
+                    <input type="file" name="file" id="file" required accept="image/*">
+                </div>
+                <button type="submit"><i class="fas fa-search"></i> Start Classification</button>
+            </form>
+
+            {% if prediction %}
+            <div class="result-box">
+                <p>Result:</p>
+                <h2
+                    style="font-size: 2.5rem; margin-top: 0.5rem; background: linear-gradient(135deg, #818cf8, #c084fc); -webkit-background-clip: text; background-clip: text; -webkit-text-fill-color: transparent;">
+                    {{ prediction }}
+                </h2>
+
+                {% if "Error" not in prediction %}
+                <div class="confidence-container">
+                    <p style="font-size: 0.875rem; color: var(--text-dim);">Confidence Score:</p>
+                    <div class="confidence-bar">
+                        <div class="confidence-fill"
+                            style="width: {{ (probability * 100) if prediction == 'Male' else ((1 - probability) * 100) }}%;">
+                        </div>
+                    </div>
+                    <p style="font-size: 0.75rem; color: var(--text-dim); text-align: right;">
+                        {{ ((probability * 100) if prediction == 'Male' else ((1 - probability) * 100))|round(2) }}%
+                    </p>
+                </div>
+                {% endif %}
+
+                {% if "Error" in prediction %}
+                <p style="color: #ef4444; margin-top: 1rem;">{{ prediction }}</p>
+                {% endif %}
+            </div>
+            {% endif %}
+        </div>
+    </div>
+
+    <script>
+        const fileInput = document.getElementById('file');
+        const previewContainer = document.getElementById('preview-container');
+        const previewImg = document.getElementById('preview-img');
+        const form = document.getElementById('upload-form');
+        const loadingOverlay = document.getElementById('loading-overlay');
+
+        fileInput.addEventListener('change', function () {
+            const file = this.files[0];
+            if (file) {
+                const reader = new FileReader();
+                reader.onload = function (e) {
+                    previewImg.src = e.target.result;
+                    previewContainer.style.display = 'block';
+                }
+                reader.readAsDataURL(file);
+            }
+        });
+
+        form.addEventListener('submit', () => {
+            loadingOverlay.style.display = 'flex';
+        });
+    </script>
+</body>
+
+</html>

templates/index.html

@@ -0,0 +1,147 @@
+{% extends "layout.html" %}
+
+{% block title %}Dashboard - Quantum AI Hub{% endblock %}
+
+{% block page_header %}
+<h1>Quantum Analytics</h1>
+<p>Select a specialized AI engine to begin processing your data.</p>
+{% endblock %}
+
+{% block content %}
+<div class="services-grid">
+  <a href="/gender" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-user-circle"></i></div>
+    <h3>Gender Discovery</h3>
+    <p>Vision Transformer model trained for high-precision gender classification.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/textgen" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-pen-nib"></i></div>
+    <h3>Text Synthesis</h3>
+    <p>Creative language generation powered by GPT-2 architecture.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/translate" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-language"></i></div>
+    <h3>Neural Translate</h3>
+    <p>Advanced English-to-Urdu translation using sequence models.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/sentiment" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-smile-beam"></i></div>
+    <h3>Empathy Engine</h3>
+    <p>Analyze emotional valence in both text and vocal inputs.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/qa" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-brain"></i></div>
+    <h3>Cognitive QA</h3>
+    <p>Extract precise knowledge from context with DistilBERT.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/zsl" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-bullseye"></i></div>
+    <h3>Zero-Shot Lab</h3>
+    <p>Powerful BART-based classification for any unseen categories.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/clustering" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-chart-pie"></i></div>
+    <h3>Data Clusters</h3>
+    <p>Automated pattern discovery using K-Means clustering.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/dbscan" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-braille"></i></div>
+    <h3>DBSCAN Lab</h3>
+    <p>Density-based clustering to identify complex patterns and outliers.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+
+  <a href="/apriori" class="service-card glass-card">
+    <div class="card-icon"><i class="fas fa-shopping-cart"></i></div>
+    <h3>Market Analytics</h3>
+    <p>Generate association rules from transactional data with A-priori.</p>
+    <div class="card-footer">
+      <span class="btn-quantum-sm">Launch Engine</span>
+    </div>
+  </a>
+</div>
+
+<style>
+  .services-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fill, minmax(300px, 1fr));
+    gap: 1.5rem;
+  }
+
+  .service-card {
+    display: flex;
+    flex-direction: column;
+    gap: 1rem;
+    text-decoration: none;
+    color: inherit;
+  }
+
+  .card-icon {
+    font-size: 2.5rem;
+    background: var(--quantum-gradient);
+    -webkit-background-clip: text;
+    -webkit-text-fill-color: transparent;
+    margin-bottom: 0.5rem;
+  }
+
+  .service-card h3 {
+    font-size: 1.4rem;
+    font-weight: 700;
+  }
+
+  .service-card p {
+    color: var(--text-secondary);
+    font-size: 0.95rem;
+    line-height: 1.6;
+    flex-grow: 1;
+  }
+
+  .card-footer {
+    margin-top: 1rem;
+    display: flex;
+    justify-content: flex-end;
+  }
+
+  .btn-quantum-sm {
+    font-size: 0.8rem;
+    text-transform: uppercase;
+    letter-spacing: 1px;
+    font-weight: 700;
+    color: var(--accent-blue);
+  }
+
+  .service-card:hover .btn-quantum-sm {
+    text-decoration: underline;
+  }
+</style>
+{% endblock %}

templates/layout.html

@@ -0,0 +1,111 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>{% block title %}AI Services Hub{% endblock %}</title>
+    <link href="https://fonts.googleapis.com/css2?family=Outfit:wght@300;400;500;600;700;800&display=swap"
+        rel="stylesheet">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css">
+    <link rel="stylesheet" href="{{ url_for('static', filename='css/main.css') }}">
+    {% block extra_css %}{% endblock %}
+</head>
+
+<body>
+    <div class="dashboard-wrapper">
+        <aside class="sidebar">
+            <div class="brand">
+                <div class="brand-icon">AI</div>
+                <span class="brand-name">Quantum Hub</span>
+            </div>
+
+            <nav class="nav-menu">
+                <a href="/" class="nav-link {% if request.path == '/' %}active{% endif %}">
+                    <i class="fas fa-th-large"></i>
+                    <span class="nav-text">Dashboard</span>
+                </a>
+                <a href="/gender" class="nav-link {% if request.path == '/gender' %}active{% endif %}">
+                    <i class="fas fa-user-circle"></i>
+                    <span class="nav-text">Gender Discovery</span>
+                </a>
+                <a href="/textgen" class="nav-link {% if request.path == '/textgen' %}active{% endif %}">
+                    <i class="fas fa-pen-nib"></i>
+                    <span class="nav-text">Text Synthesis</span>
+                </a>
+                <a href="/translate" class="nav-link {% if request.path == '/translate' %}active{% endif %}">
+                    <i class="fas fa-language"></i>
+                    <span class="nav-text">Neural Translate</span>
+                </a>
+                <a href="/sentiment" class="nav-link {% if request.path == '/sentiment' %}active{% endif %}">
+                    <i class="fas fa-smile-beam"></i>
+                    <span class="nav-text">Empathy Engine</span>
+                </a>
+                <a href="/qa" class="nav-link {% if request.path == '/qa' %}active{% endif %}">
+                    <i class="fas fa-brain"></i>
+                    <span class="nav-text">Cognitive QA</span>
+                </a>
+                <a href="/zsl" class="nav-link {% if request.path == '/zsl' %}active{% endif %}">
+                    <i class="fas fa-bullseye"></i>
+                    <span class="nav-text">Zero-Shot Lab</span>
+                </a>
+                <a href="/clustering" class="nav-link {% if request.path == '/clustering' %}active{% endif %}">
+                    <i class="fas fa-chart-pie"></i>
+                    <span class="nav-text">Data Clusters</span>
+                </a>
+                <a href="/dbscan" class="nav-link {% if request.path == '/dbscan' %}active{% endif %}">
+                    <i class="fas fa-braille"></i>
+                    <span class="nav-text">DBSCAN Clusters</span>
+                </a>
+                <a href="/apriori" class="nav-link {% if request.path == '/apriori' %}active{% endif %}">
+                    <i class="fas fa-shopping-cart"></i>
+                    <span class="nav-text">Association Rules</span>
+                </a>
+            </nav>
+        </aside>
+
+        <main class="main-content">
+            <header class="top-bar">
+                <div class="page-title">
+                    {% block page_header %}{% endblock %}
+                </div>
+                <div class="user-profile">
+                    <div class="status-pill">
+                        <span class="dot"></span> Online
+                    </div>
+                </div>
+            </header>
+
+            <section class="content-area animate-fade-in">
+                {% block content %}{% endblock %}
+            </section>
+        </main>
+    </div>
+
+    <style>
+        .status-pill {
+            background: rgba(34, 197, 94, 0.1);
+            color: #22c55e;
+            padding: 6px 12px;
+            border-radius: 999px;
+            font-size: 0.85rem;
+            font-weight: 600;
+            display: flex;
+            align-items: center;
+            gap: 8px;
+            border: 1px solid rgba(34, 197, 94, 0.2);
+        }
+
+        .status-pill .dot {
+            width: 8px;
+            height: 8px;
+            background: #22c55e;
+            border-radius: 50%;
+            box-shadow: 0 0 10px #22c55e;
+        }
+    </style>
+
+    {% block extra_js %}{% endblock %}
+</body>
+
+</html>

templates/qa.html

@@ -0,0 +1,262 @@
+{% extends "layout.html" %}
+
+{% block title %}Cognitive QA - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Cognitive QA</h1>
+<p>Knowledge extraction engine with vocal synthesis output.</p>
+<script>
+  function switchTab(type) {
+    document.querySelectorAll('.tab-btn').forEach(b => b.classList.remove('active'));
+    document.querySelectorAll('.tab-content').forEach(c => c.classList.remove('active'));
+
+    event.currentTarget.classList.add('active');
+    document.getElementById(type + 'Section').classList.add('active');
+  }
+</script>
+{% endblock %}
+
+{% block content %}
+<div class="qa-container">
+  <div class="glass-card">
+    <form action="/qa" method="post" enctype="multipart/form-data" class="quantum-form">
+      <div class="input-group">
+        <label>Context Repository</label>
+        <textarea name="context" placeholder="Paste the reference document here..."
+          required>{{ context or '' }}</textarea>
+      </div>
+
+      <div class="tabs">
+        <button type="button" class="tab-btn active" onclick="switchTab('text')">Type Question</button>
+        <button type="button" class="tab-btn" onclick="switchTab('voice')">Voice Question</button>
+      </div>
+
+      <div id="textSection" class="tab-content active">
+        <div class="input-group">
+          <label>Query Expression</label>
+          <div class="search-input">
+            <input type="text" name="question" placeholder="Ask a question about the context..."
+              value="{{ question or '' }}">
+            <i class="fas fa-search"></i>
+          </div>
+        </div>
+      </div>
+
+      <div id="voiceSection" class="tab-content">
+        <div class="upload-zone">
+          <i class="fas fa-microphone-alt upload-icon"></i>
+          <div class="upload-text">
+            <strong>Record Your Query</strong>
+            <span>Upload audio for voice-to-voice QA</span>
+          </div>
+          <input type="file" name="voice" accept="audio/*">
+        </div>
+      </div>
+
+      <button type="submit" class="btn-quantum full-width">
+        <i class="fas fa-brain"></i> Execute Reasoning
+      </button>
+    </form>
+
+    {% if answer %}
+    <div class="result-container animate-fade-in">
+      <div class="result-header">Reasoning Output</div>
+      <div class="answer-box">
+        <div class="answer-text">
+          <label>Extracted Answer</label>
+          <p>{{ answer }}</p>
+        </div>
+
+        <div class="vocal-playback">
+          <audio id="vocalOutput"
+            src="{{ url_for('static', filename='answer.mp3') }}?v={{ range(1, 99999)|random }}"></audio>
+          <button type="button" class="btn-playback" onclick="document.getElementById('vocalOutput').play()">
+            <i class="fas fa-volume-up"></i>
+          </button>
+        </div>
+      </div>
+
+      {% if score %}
+      <div class="confidence-meter">
+        <div class="meter-track">
+          <div class="meter-fill" style="width: {{ score }}%"></div>
+        </div>
+        <div class="meter-info">
+          <span>Confidence Score</span>
+          <span>{{ score }}%</span>
+        </div>
+      </div>
+      {% endif %}
+    </div>
+    {% endif %}
+  </div>
+</div>
+
+<style>
+  .qa-container {
+    max-width: 900px;
+    margin: 0 auto;
+  }
+
+  textarea {
+    width: 100%;
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1.25rem;
+    color: var(--text-primary);
+    font-size: 1rem;
+    min-height: 200px;
+    line-height: 1.6;
+  }
+
+  .search-input {
+    position: relative;
+  }
+
+  .search-input input {
+    width: 100%;
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1rem 1rem 1rem 3rem;
+    color: var(--text-primary);
+    font-size: 1.1rem;
+  }
+
+  .search-input i {
+    position: absolute;
+    left: 1rem;
+    top: 50%;
+    transform: translateY(-50%);
+    color: var(--accent-blue);
+  }
+
+  .tabs {
+    display: flex;
+    gap: 1rem;
+    margin-bottom: 2rem;
+    border-bottom: 1px solid var(--glass-border);
+    padding-bottom: 1rem;
+  }
+
+  .tab-btn {
+    background: transparent;
+    border: none;
+    color: var(--text-secondary);
+    font-weight: 600;
+    cursor: pointer;
+    padding: 0.5rem 1rem;
+    transition: var(--transition);
+    border-radius: var(--radius-md);
+  }
+
+  .tab-btn.active {
+    color: var(--accent-blue);
+    background: rgba(0, 210, 255, 0.1);
+  }
+
+  .tab-content {
+    display: none;
+  }
+
+  .tab-content.active {
+    display: block;
+  }
+
+  .upload-zone {
+    border: 2px dashed var(--glass-border);
+    border-radius: var(--radius-lg);
+    padding: 2.5rem;
+    text-align: center;
+    position: relative;
+    background: rgba(0, 0, 0, 0.1);
+    margin-bottom: 1.5rem;
+  }
+
+  .upload-zone input {
+    position: absolute;
+    inset: 0;
+    opacity: 0;
+    cursor: pointer;
+  }
+
+  .upload-icon {
+    font-size: 2.5rem;
+    color: var(--accent-blue);
+    margin-bottom: 1rem;
+    display: block;
+  }
+
+  .answer-box {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    background: rgba(0, 210, 255, 0.05);
+    padding: 2rem;
+    border-radius: var(--radius-md);
+    margin-bottom: 2rem;
+    border-left: 5px solid var(--accent-blue);
+  }
+
+  .answer-text label {
+    font-size: 0.75rem;
+    font-weight: 800;
+    text-transform: uppercase;
+    color: var(--accent-blue);
+    margin-bottom: 0.5rem;
+    display: block;
+  }
+
+  .answer-text p {
+    font-size: 1.5rem;
+    font-weight: 700;
+    color: var(--text-primary);
+  }
+
+  .btn-playback {
+    width: 60px;
+    height: 60px;
+    border-radius: 50%;
+    background: var(--quantum-gradient);
+    border: none;
+    color: white;
+    font-size: 1.5rem;
+    cursor: pointer;
+    display: grid;
+    place-items: center;
+    transition: var(--transition);
+  }
+
+  .btn-playback:hover {
+    transform: scale(1.1);
+    box-shadow: 0 0 20px rgba(0, 210, 255, 0.4);
+  }
+
+  .confidence-meter {
+    margin-top: 1rem;
+  }
+
+  .meter-track {
+    height: 8px;
+    background: rgba(255, 255, 255, 0.1);
+    border-radius: 4px;
+    overflow: hidden;
+    margin-bottom: 0.5rem;
+  }
+
+  .meter-fill {
+    height: 100%;
+    background: var(--quantum-gradient);
+    box-shadow: 0 0 10px rgba(0, 210, 255, 0.5);
+  }
+
+  .meter-info {
+    display: flex;
+    justify-content: space-between;
+    color: var(--text-secondary);
+    font-size: 0.85rem;
+    font-weight: 600;
+  }
+</style>
+{% endblock %}

templates/sentiment.html

@@ -0,0 +1,210 @@
+{% extends "layout.html" %}
+
+{% block title %}Empathy Engine - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Empathy Engine</h1>
+<p>Contextual sentiment analysis for text and vocal recordings.</p>
+{% endblock %}
+
+{% block content %}
+<div class="sentiment-container">
+  <div class="glass-card sentiment-analyzer">
+    <form action="/sentiment" method="post" enctype="multipart/form-data" class="quantum-form">
+      <div class="tabs">
+        <button type="button" class="tab-btn active" onclick="switchTab('text')">Text Analysis</button>
+        <button type="button" class="tab-btn" onclick="switchTab('voice')">Vocal Analysis</button>
+      </div>
+
+      <div id="textSection" class="tab-content active">
+        <div class="input-group">
+          <label>Input Text</label>
+          <textarea name="text" placeholder="Explain how you're feeling..."></textarea>
+        </div>
+      </div>
+
+      <div id="voiceSection" class="tab-content">
+        <div class="upload-zone">
+          <i class="fas fa-microphone-alt upload-icon"></i>
+          <div class="upload-text">
+            <strong>Upload Voice Recording</strong>
+            <span>WAV or MP3 format required</span>
+          </div>
+          <input type="file" name="voice" accept="audio/*">
+        </div>
+      </div>
+
+      <button type="submit" class="btn-quantum full-width">
+        <i class="fas fa-heartbeat"></i> Analyze Sentiment
+      </button>
+    </form>
+
+    {% if result %}
+    <div class="result-container animate-fade-in">
+      <div class="result-header">Engine Output</div>
+
+      {% if transcript %}
+      <div class="transcript-box">
+        <label>Vocal Transcription</label>
+        <p>"{{ transcript }}"</p>
+      </div>
+      {% endif %}
+
+      <div class="sentiment-meter">
+        <div class="meter-label">
+          <span>Detected Sentiment</span>
+          <span class="sentiment-value highlight-{{ result|lower }}">{{ result }}</span>
+        </div>
+        <!-- Simple visual score if available, or just a themed box -->
+        <div class="sentiment-score-box {{ result|lower }}">
+          {% if result|lower == 'positive' %}
+          <i class="fas fa-laugh-beam"></i>
+          {% elif result|lower == 'negative' %}
+          <i class="fas fa-frown-open"></i>
+          {% else %}
+          <i class="fas fa-meh"></i>
+          {% endif %}
+        </div>
+      </div>
+    </div>
+    {% endif %}
+  </div>
+</div>
+
+<style>
+  .sentiment-container {
+    max-width: 800px;
+    margin: 0 auto;
+  }
+
+  .tabs {
+    display: flex;
+    gap: 1rem;
+    margin-bottom: 2rem;
+    border-bottom: 1px solid var(--glass-border);
+    padding-bottom: 1rem;
+  }
+
+  .tab-btn {
+    background: transparent;
+    border: none;
+    color: var(--text-secondary);
+    font-weight: 600;
+    cursor: pointer;
+    padding: 0.5rem 1rem;
+    transition: var(--transition);
+    border-radius: var(--radius-md);
+  }
+
+  .tab-btn.active {
+    color: var(--accent-blue);
+    background: rgba(0, 210, 255, 0.1);
+  }
+
+  .tab-content {
+    display: none;
+  }
+
+  .tab-content.active {
+    display: block;
+  }
+
+  .upload-zone {
+    border: 2px dashed var(--glass-border);
+    border-radius: var(--radius-lg);
+    padding: 2.5rem;
+    text-align: center;
+    position: relative;
+  }
+
+  .upload-zone input {
+    position: absolute;
+    inset: 0;
+    opacity: 0;
+    cursor: pointer;
+  }
+
+  .transcript-box {
+    margin-bottom: 1.5rem;
+    padding: 1rem;
+    background: rgba(0, 0, 0, 0.2);
+    border-radius: var(--radius-md);
+  }
+
+  .transcript-box label {
+    font-size: 0.75rem;
+    font-weight: 800;
+    text-transform: uppercase;
+    color: var(--accent-blue);
+  }
+
+  .sentiment-meter {
+    display: flex;
+    align-items: center;
+    gap: 2rem;
+    background: rgba(255, 255, 255, 0.03);
+    padding: 1.5rem;
+    border-radius: var(--radius-md);
+  }
+
+  .meter-label {
+    display: flex;
+    flex-direction: column;
+    flex-grow: 1;
+  }
+
+  .sentiment-value {
+    font-size: 2.5rem;
+    font-weight: 800;
+    text-transform: capitalize;
+  }
+
+  .highlight-positive {
+    color: #22c55e;
+  }
+
+  .highlight-negative {
+    color: #ef4444;
+  }
+
+  .highlight-neutral {
+    color: var(--accent-blue);
+  }
+
+  .sentiment-score-box {
+    font-size: 3.5rem;
+  }
+
+  .sentiment-score-box.positive {
+    color: #22c55e;
+  }
+
+  .sentiment-score-box.negative {
+    color: #ef4444;
+  }
+
+  .sentiment-score-box.neutral {
+    color: var(--accent-blue);
+  }
+
+  textarea {
+    width: 100%;
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1rem;
+    color: var(--text-primary);
+    min-height: 150px;
+  }
+</style>
+
+<script>
+  function switchTab(type) {
+    document.querySelectorAll('.tab-btn').forEach(b => b.classList.remove('active'));
+    document.querySelectorAll('.tab-content').forEach(c => c.classList.remove('active'));
+
+    event.target.classList.add('active');
+    document.getElementById(type + 'Section').classList.add('active');
+  }
+</script>
+{% endblock %}

templates/textgen.html

@@ -0,0 +1,97 @@
+{% extends "layout.html" %}
+
+{% block title %}Text Synthesis - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Text Synthesis</h1>
+<p>Neural text generation powered by GPT-2 architecture.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+  <form action="/textgen" method="post" class="quantum-form">
+    <div class="input-group">
+      <label for="prompt">Synthesis Prompt</label>
+      <textarea id="prompt" name="prompt" placeholder="Enter a seed sentence for the AI to expand upon..."
+        required></textarea>
+    </div>
+
+    <button type="submit" class="btn-quantum full-width">
+      <i class="fas fa-magic"></i> Synthesize Text
+    </button>
+  </form>
+
+  {% if generated_text %}
+  <div class="result-container animate-fade-in">
+    <div class="result-header">Engine Output</div>
+    <div class="result-display text-output">
+      {{ generated_text }}
+    </div>
+    <div class="result-note">
+      <i class="fas fa-info-circle"></i> Output is generated token-by-token based on probability distributions.
+    </div>
+  </div>
+  {% endif %}
+</div>
+
+<style>
+  .service-panel {
+    max-width: 800px;
+    margin: 0 auto;
+  }
+
+  .quantum-form {
+    display: flex;
+    flex-direction: column;
+    gap: 1.5rem;
+  }
+
+  .input-group {
+    display: flex;
+    flex-direction: column;
+    gap: 0.5rem;
+  }
+
+  .input-group label {
+    font-weight: 600;
+    color: var(--text-secondary);
+    font-size: 0.9rem;
+    text-transform: uppercase;
+    letter-spacing: 1px;
+  }
+
+  textarea {
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1rem;
+    color: var(--text-primary);
+    font-size: 1.1rem;
+    min-height: 120px;
+    resize: vertical;
+    transition: var(--transition);
+  }
+
+  textarea:focus {
+    outline: none;
+    border-color: var(--accent-blue);
+    background: rgba(0, 210, 255, 0.05);
+  }
+
+  .full-width {
+    width: 100%;
+    justify-content: center;
+    padding: 1rem;
+  }
+
+  .text-output {
+    line-height: 1.8;
+    font-size: 1.1rem;
+    white-space: pre-wrap;
+    background: rgba(255, 255, 255, 0.03);
+    padding: 2rem;
+    border-radius: var(--radius-md);
+    border-left: 4px solid var(--accent-blue);
+  }
+</style>
+{% endblock %}

templates/translate.html

@@ -0,0 +1,112 @@
+{% extends "layout.html" %}
+
+{% block title %}Neural Translate - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Neural Translate</h1>
+<p>Context-aware English to Urdu sequence-to-sequence translation.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+  <form action="/translate" method="post" class="quantum-form">
+    <div class="translation-grid">
+      <div class="input-group">
+        <label>Source (English)</label>
+        <textarea name="text" placeholder="Enter text to translate..." required></textarea>
+      </div>
+      <div class="input-group">
+        <label>Target (Urdu)</label>
+        <div class="output-area {% if translated_text %}active{% endif %}">
+          {% if translated_text %}
+          {{ translated_text }}
+          {% else %}
+          <span class="placeholder">Translation will appear here...</span>
+          {% endif %}
+        </div>
+      </div>
+    </div>
+
+    <button type="submit" class="btn-quantum full-width">
+      <i class="fas fa-sync-alt"></i> Execute Translation
+    </button>
+  </form>
+</div>
+
+<style>
+  .service-panel {
+    max-width: 1000px;
+    margin: 0 auto;
+  }
+
+  .translation-grid {
+    display: grid;
+    grid-template-columns: 1fr 1fr;
+    gap: 1.5rem;
+    margin-bottom: 1.5rem;
+  }
+
+  .input-group {
+    display: flex;
+    flex-direction: column;
+    gap: 0.5rem;
+  }
+
+  .input-group label {
+    font-weight: 600;
+    color: var(--text-secondary);
+    font-size: 0.85rem;
+    text-transform: uppercase;
+    letter-spacing: 1px;
+  }
+
+  textarea,
+  .output-area {
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1.25rem;
+    color: var(--text-primary);
+    font-size: 1.2rem;
+    min-height: 250px;
+    transition: var(--transition);
+  }
+
+  .output-area {
+    display: flex;
+    align-items: flex-start;
+    justify-content: flex-start;
+    direction: rtl;
+    /* Urdu is RTL */
+    font-family: 'Noto Nastaliq Urdu', serif;
+  }
+
+  .output-area.active {
+    background: rgba(0, 210, 255, 0.03);
+  }
+
+  .output-area .placeholder {
+    color: var(--text-secondary);
+    font-size: 1rem;
+    font-family: 'Outfit', sans-serif;
+    direction: ltr;
+  }
+
+  textarea:focus {
+    outline: none;
+    border-color: var(--accent-blue);
+  }
+
+  .full-width {
+    width: 100%;
+    justify-content: center;
+    padding: 1rem;
+  }
+
+  @media (max-width: 768px) {
+    .translation-grid {
+      grid-template-columns: 1fr;
+    }
+  }
+</style>
+{% endblock %}

templates/zsl.html

@@ -0,0 +1,177 @@
+{% extends "layout.html" %}
+
+{% block title %}Zero-Shot Lab - Quantum AI{% endblock %}
+
+{% block page_header %}
+<h1>Zero-Shot Lab</h1>
+<p>Dynamic classification engine for unforeseen data categories.</p>
+{% endblock %}
+
+{% block content %}
+<div class="service-panel glass-card">
+  <form action="/zsl" method="post" class="quantum-form">
+    <div class="input-group">
+      <label>Abstract Data Input</label>
+      <textarea name="text" placeholder="Enter the content you wish to classify..." required></textarea>
+    </div>
+
+    <div class="input-group">
+      <label>Candidate Categories (Comma Separated)</label>
+      <input type="text" name="labels" placeholder="e.g. Finance, Technology, Health, Sports" required>
+    </div>
+
+    <button type="submit" class="btn-quantum full-width">
+      <i class="fas fa-bullseye"></i> Initialize Zero-Shot Analysis
+    </button>
+  </form>
+
+  {% if error %}
+  <div class="error-msg animate-fade-in">
+    <i class="fas fa-exclamation-triangle"></i> {{ error }}
+  </div>
+  {% endif %}
+
+  {% if result %}
+  <div class="result-container animate-fade-in">
+    <div class="result-header">Engine Output</div>
+
+    <div class="best-prediction">
+      <label>Highest Probability Fit</label>
+      <div class="prediction-value">
+        <span class="category">{{ result.label }}</span>
+        <span class="confidence">{{ result.score }}% Confidence</span>
+      </div>
+    </div>
+
+    <div class="detailed-results">
+      <label>Category Distributions</label>
+      <div class="result-grid">
+        {% for label, score in result.all_results %}
+        <div class="result-row">
+          <div class="row-info">
+            <span>{{ label }}</span>
+            <span>{{ score }}%</span>
+          </div>
+          <div class="row-bar">
+            <div class="bar-fill" style="width: {{ score }}%"></div>
+          </div>
+        </div>
+        {% endfor %}
+      </div>
+    </div>
+  </div>
+  {% endif %}
+</div>
+
+<style>
+  .service-panel {
+    max-width: 850px;
+    margin: 0 auto;
+  }
+
+  textarea {
+    width: 100%;
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1.25rem;
+    color: var(--text-primary);
+    min-height: 150px;
+  }
+
+  input[type="text"] {
+    width: 100%;
+    background: rgba(0, 0, 0, 0.2);
+    border: 1px solid var(--glass-border);
+    border-radius: var(--radius-md);
+    padding: 1rem;
+    color: var(--text-primary);
+    font-size: 1.1rem;
+  }
+
+  .best-prediction {
+    background: rgba(0, 210, 255, 0.05);
+    padding: 2rem;
+    border-radius: var(--radius-md);
+    margin-bottom: 2rem;
+    border-right: 4px solid var(--accent-blue);
+  }
+
+  .best-prediction label {
+    font-size: 0.75rem;
+    font-weight: 800;
+    text-transform: uppercase;
+    color: var(--accent-blue);
+    margin-bottom: 0.5rem;
+    display: block;
+  }
+
+  .prediction-value {
+    display: flex;
+    justify-content: space-between;
+    align-items: baseline;
+  }
+
+  .prediction-value .category {
+    font-size: 2.2rem;
+    font-weight: 800;
+    color: var(--text-primary);
+  }
+
+  .prediction-value .confidence {
+    font-size: 1.2rem;
+    font-weight: 600;
+    color: var(--accent-purple);
+  }
+
+  .detailed-results label {
+    color: var(--text-secondary);
+    font-weight: 600;
+    font-size: 0.9rem;
+    margin-bottom: 1rem;
+    display: block;
+  }
+
+  .result-grid {
+    display: flex;
+    flex-direction: column;
+    gap: 1.25rem;
+  }
+
+  .result-row {
+    display: flex;
+    flex-direction: column;
+    gap: 0.5rem;
+  }
+
+  .row-info {
+    display: flex;
+    justify-content: space-between;
+    font-weight: 600;
+    font-size: 0.95rem;
+  }
+
+  .row-bar {
+    height: 6px;
+    background: rgba(255, 255, 255, 0.05);
+    border-radius: 3px;
+    overflow: hidden;
+  }
+
+  .bar-fill {
+    height: 100%;
+    background: var(--quantum-gradient);
+  }
+
+  .error-msg {
+    margin-top: 1rem;
+    background: rgba(239, 68, 68, 0.1);
+    color: #ef4444;
+    padding: 1rem;
+    border-radius: var(--radius-md);
+    display: flex;
+    align-items: center;
+    gap: 10px;
+  }
+</style>
+{% endblock %}

train_cnn.py

@@ -0,0 +1,123 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader
+from torchvision import datasets, transforms
+import os
+
+# --- Improved CNN Architecture ---
+class GenderCNN(nn.Module):
+    def __init__(self):
+        super(GenderCNN, self).__init__()
+
+        self.conv_layers = nn.Sequential(
+            # Block 1
+            nn.Conv2d(3, 32, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(32),
+            nn.MaxPool2d(2, 2),
+
+            # Block 2
+            nn.Conv2d(32, 64, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(64),
+            nn.MaxPool2d(2, 2),
+
+            # Block 3 (New Layer for better features)
+            nn.Conv2d(64, 128, kernel_size=3, padding=1),
+            nn.ReLU(),
+            nn.BatchNorm2d(128),
+            nn.MaxPool2d(2, 2)
+        )
+
+        self.fc_layers = nn.Sequential(
+            nn.Flatten(),
+            # Input to linear: 128 * (128/2/2/2) * (128/2/2/2) = 128 * 16 * 16
+            nn.Linear(128 * 16 * 16, 256),
+            nn.ReLU(),
+            nn.Dropout(0.5), # Add dropout to prevent overfitting
+            nn.Linear(256, 1),
+            nn.Sigmoid()
+        )
+
+    def forward(self, x):
+        x = self.conv_layers(x)
+        x = self.fc_layers(x)
+        return x
+
+def main():
+    print("--- Starting Improved CNN Training Loop ---")
+    
+    # Device configuration
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+    print(f"Using device: {device}")
+
+    # Set Paths - USER MUST ENSURE DATA IS IN THESE FOLDERS
+    # Defaulting to a local 'dataset' folder in the current directory
+    data_dir = 'dataset'
+    train_path = os.path.join(data_dir, 'train')
+    
+    if not os.path.exists(train_path):
+        print(f"ERROR: Training path not found at {train_path}")
+        print("Please place your images in: dataset/train/Male and dataset/train/Female")
+        return
+
+    # Hyperparameters
+    epochs = 10
+    batch_size = 32
+    learning_rate = 0.001
+    
+    # Transforms
+    transform = transforms.Compose([
+        transforms.Resize((128, 128)),
+        transforms.RandomHorizontalFlip(), # Data augmentation
+        transforms.ToTensor(),
+        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
+    ])
+
+    # Data Loader
+    train_dataset = datasets.ImageFolder(root=train_path, transform=transform)
+    dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
+    
+    print(f"Dataset found with classes: {train_dataset.classes}")
+    # Note: Ensure Male is index 1 or adapt the mapping. Usually ImageFolder sorts alphabetically.
+    # Female: 0, Male: 1 matches the original logic.
+
+    # Initialize Model, Loss, and Optimizer
+    model = GenderCNN().to(device)
+    criterion = nn.BCELoss()
+    optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+    
+    # Training Loop
+    model.train()
+    for epoch in range(epochs):
+        epoch_loss = 0
+        correct = 0
+        total = 0
+        
+        for images, labels in dataloader:
+            images = images.to(device)
+            labels = labels.float().unsqueeze(1).to(device)
+            
+            optimizer.zero_grad()
+            outputs = model(images)
+            loss = criterion(outputs, labels)
+            loss.backward()
+            optimizer.step()
+            
+            epoch_loss += loss.item()
+            predictions = (outputs > 0.5).float()
+            correct += (predictions == labels).sum().item()
+            total += labels.size(0)
+            
+        avg_loss = epoch_loss / len(dataloader)
+        accuracy = (correct / total) * 100
+        print(f"Epoch [{epoch+1}/{epochs}] - Loss: {avg_loss:.4f} - Accuracy: {accuracy:.2f}%")
+
+    # Save Model
+    os.makedirs('models', exist_ok=True)
+    torch.save(model.state_dict(), 'models/gender_model.pth')
+    print("\nTraining Complete! Model saved to models/gender_model.pth")
+
+if __name__ == '__main__':
+    main()

verify_extended.py

@@ -0,0 +1,58 @@
+
+import sys
+import os
+import torch
+import numpy as np
+import pandas as pd
+import librosa
+from models_loader import loader
+
+def test_extended():
+    print("--- Starting Extended Model Verification ---")
+
+    # 1. STT (Speech to Text)
+    print("\nTesting STT (Whisper)...")
+    if loader.stt_pipeline:
+        try:
+            # Create a 1-second silent audio array
+            audio_array = np.zeros(16000, dtype=np.float32)
+            res = loader.stt_pipeline(audio_array)
+            print(f"STT Result: {res}")
+        except Exception as e:
+            print(f"FAILED: STT pipeline error: {e}")
+    else:
+        print("FAILED: STT pipeline not loaded")
+
+    # 2. DBSCAN
+    print("\nTesting DBSCAN...")
+    try:
+        from sklearn.cluster import DBSCAN
+        data = np.random.rand(10, 2)
+        db = DBSCAN(eps=0.3, min_samples=2).fit(data)
+        print(f"DBSCAN labels: {db.labels_}")
+    except Exception as e:
+        print(f"FAILED: DBSCAN error: {e}")
+
+    # 3. Apriori
+    print("\nTesting Apriori...")
+    try:
+        from mlxtend.frequent_patterns import apriori, association_rules
+        from mlxtend.preprocessing import TransactionEncoder
+        dataset = [['Milk', 'Onion', 'Nut', 'Kidney Beans', 'Eggs', 'Yogurt'],
+                   ['Dill', 'Onion', 'Nut', 'Kidney Beans', 'Eggs', 'Yogurt'],
+                   ['Milk', 'Apple', 'Kidney Beans', 'Eggs'],
+                   ['Milk', 'Unicorn', 'Corn', 'Kidney Beans', 'Yogurt'],
+                   ['Corn', 'Onion', 'Onion', 'Kidney Beans', 'Ice cream', 'Eggs']]
+        te = TransactionEncoder()
+        te_ary = te.fit(dataset).transform(dataset)
+        df = pd.DataFrame(te_ary, columns=te.columns_)
+        freq = apriori(df, min_support=0.6, use_colnames=True)
+        rules = association_rules(freq, metric="lift", min_threshold=0.7)
+        print(f"Apriori rules found: {len(rules)}")
+    except Exception as e:
+        print(f"FAILED: Apriori error: {e}")
+
+    print("\n--- Extended Verification Complete ---")
+
+if __name__ == "__main__":
+    test_extended()

verify_models.py

@@ -0,0 +1,68 @@
+import sys
+import os
+
+# Add current directory to path
+sys.path.append(os.getcwd())
+
+from models_loader import loader
+import torch
+from PIL import Image
+import numpy as np
+
+def test_models():
+    print("--- Starting Model Verification ---")
+    
+    # 1. Sentiment
+    print("\nTesting Sentiment Analysis...")
+    if loader.sentiment_pipeline:
+        res = loader.sentiment_pipeline("I love this project!")
+        print(f"Result: {res}")
+    else:
+        print("FAILED: Sentiment pipeline not loaded")
+
+    # 2. QA
+    print("\nTesting Question Answering...")
+    if loader.qa_pipeline:
+        res = loader.qa_pipeline(question="What is this?", context="This is a test.")
+        print(f"Result: {res}")
+    else:
+        print("FAILED: QA pipeline not loaded")
+
+    # 3. Translation
+    print("\nTesting Translation (MT-EN-UR)...")
+    if loader.translator_pipeline:
+        res = loader.translator_pipeline("Hello, how are you?")
+        print(f"Result: {res}")
+    else:
+        print("FAILED: Translation pipeline not loaded")
+
+    # 4. Text Gen
+    print("\nTesting Text Generation...")
+    if loader.text_gen_pipeline:
+        res = loader.text_gen_pipeline("Once upon a time", max_length=20)
+        print(f"Result: {res}")
+    else:
+        print("FAILED: Text Gen pipeline not loaded")
+
+    # 5. ZSL
+    print("\nTesting Zero-Shot Learning...")
+    if loader.zsl_pipeline:
+        res = loader.zsl_pipeline("This is about sports.", candidate_labels=["politics", "sports", "cooking"])
+        print(f"Result: {res['labels'][0]}")
+    else:
+        print("FAILED: ZSL pipeline not loaded")
+
+    # 6. Gender Classifier (Mini)
+    print("\nTesting Image Classification (Gender)...")
+    if loader.gender_classifier:
+        # Create a dummy image
+        dummy_img = Image.fromarray(np.uint8(np.random.rand(224,224,3)*255))
+        res = loader.gender_classifier(dummy_img)
+        print(f"Result: {res}")
+    else:
+        print("FAILED: Gender classifier pipeline not loaded")
+
+    print("\n--- Verification Complete ---")
+
+if __name__ == "__main__":
+    test_models()