Update app.py

app.py

@@ -1,4 +1,4 @@
-# imports
+# --- IMPORTS ---
 import gradio as gr
 from huggingface_hub import InferenceClient
 import re
@@ -10,41 +10,28 @@ import torchvision.transforms as transforms
 import torchvision.models as models
 from PIL import Image
 
+# --- LOAD MODELS ---
 
-# Load ResNet18 model
+# HuggingFace Zephyr Model for Chat
+client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+# Whisper Model for Audio-to-Text
+whisper_model = whisper.load_model("base")
+
+# ResNet18 Model for Posture Classification
 model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
-model.fc = torch.nn.Linear(model.fc.in_features, 2)  # Adjust for two classes
+model.fc = torch.nn.Linear(model.fc.in_features, 2)
 model.eval()
 
-# Define image transformation
 transform = transforms.Compose([
     transforms.Resize((224, 224)),
     transforms.ToTensor()
 ])
 
-# Function to classify posture images
-def classify_image(image):
-    if image is None:
-        return "No image provided! Please upload or capture an image."
-    
-    image = transform(image).unsqueeze(0)
-    output = model(image)
-    _, predicted = torch.max(output, 1)
-    return (
-        "Good Posture! Sit exactly like that for your Interview!" 
-        if predicted.item() == 0 
-        else "Bad Posture, you should think of sitting a little straighter or more in frame for your real interview."
-    )
-
-# Set up Gradio interface
-iface = gr.Interface(fn=classify_image, inputs=gr.Image(type="pil"), outputs="text")
-iface.launch()
-
-# uploading and cleaning the knowledge txt file
+# --- LOAD QUESTIONS ---
 def load_questions(file_path):
     with open(file_path, 'r') as f:
         data = f.read()
-
     question_blocks = re.split(r'Question:\s*', data)[1:]
     questions = []
     for block in question_blocks:
@@ -57,7 +44,6 @@ def load_questions(file_path):
 
 all_questions = load_questions('knowledge.txt')
 
-# creating the questions based on each interview
 questions_by_type = {
     'Technical': [q for q in all_questions if any(keyword in q['question'].lower() for keyword in [
         'function', 'linked list', 'url', 'rest', 'graphql', 'garbage', 'cap theorem', 'sql', 'hash table',
@@ -70,14 +56,9 @@ questions_by_type = {
         "testing", "financial", "automation", "analysis", "regression", "business", "stakeholder"])] 
 }
 
-# models
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-whisper_model = whisper.load_model("base")
-
-# whisper audio-to-text function
+# --- AUDIO TRANSCRIPTION ---
 def transcribe_audio(file_path):
     try:
-        print(f"📂 Processing audio: {file_path}")
         audio = AudioSegment.from_file(file_path)
         converted_path = "converted.wav"
         audio.export(converted_path, format="wav")
@@ -86,17 +67,29 @@ def transcribe_audio(file_path):
     except Exception as e:
         return f"❌ ERROR: {str(e)}"
 
-# setting up the users profile (step 1)
+# --- POSTURE CLASSIFICATION ---
+def classify_image(image):
+    if image is None:
+        return "No image provided! Please upload or capture an image."
+    image = transform(image).unsqueeze(0)
+    output = model(image)
+    _, predicted = torch.max(output, 1)
+    return (
+        "✅ Good Posture! Sit exactly like that for your Interview!" 
+        if predicted.item() == 0 
+        else "⚠️ Bad Posture — try sitting straighter or more centered for your real interview."
+    )
+
+# --- INTERVIEW LOGIC ---
+
 def set_type(choice, user_profile):
     user_profile["interview_type"] = choice
     return "Great! What’s your background and what field/role are you aiming for?", user_profile
 
-# step 2
 def save_background(info, user_profile):
     user_profile["field"] = info
     return "Awesome! Type 'start' below to begin your interview.", user_profile
 
-# step 3
 def respond(message, chat_history, user_profile):
     message_lower = message.strip().lower()
 
@@ -105,7 +98,6 @@ def respond(message, chat_history, user_profile):
         chat_history.append((message, bot_msg))
         return chat_history
 
-    # interview process
     if message_lower == 'start':
         interview_type = user_profile['interview_type']
         selected_questions = questions_by_type.get(interview_type, [])
@@ -149,7 +141,6 @@ def respond(message, chat_history, user_profile):
         chat_history.append((message, feedback))
         return chat_history
 
-    # starting the chatbot
     messages = [{"role": "system", "content": f"You are a professional interviewer conducting a {user_profile['interview_type']} interview for a candidate in {user_profile['field']}."}]
     for q, a in chat_history:
         messages.append({"role": "user", "content": q})
@@ -171,11 +162,11 @@ def generate_feedback(user_profile):
         if match:
             fb = f"Question {i+1}: ✅ Good job!"
         else:
-            fb = f"Question {i+1}: ❌ Missed some key points: {correct_answers[0]}"
+            fb = f"Question {i+1}: ❌ Missed key points: {correct_answers[0]}"
         feedback.append(fb)
     return "\n".join(feedback)
 
-# handle audio input
+# AUDIO HANDLING
 def handle_audio(audio_file, chat_history, user_profile):
     transcribed = transcribe_audio(audio_file)
     if transcribed.startswith("❌"):
@@ -183,12 +174,13 @@ def handle_audio(audio_file, chat_history, user_profile):
         return chat_history
     return respond(transcribed, chat_history, user_profile)
 
-# creating the visual elements
+# --- GRADIO INTERFACE ---
+
 with gr.Blocks() as demo:
     user_profile = gr.State({"interview_type": "", "field": "", "interview_in_progress": False})
     chat_history = gr.State([])
 
-    gr.Markdown("# Welcome to Intervu")
+    gr.Markdown("# 🎤 Welcome to Intervu")
     gr.Image(value="images.JPEG", show_label=False, width=200)
 
     gr.Markdown("### Step 1: Choose Interview Type")
@@ -207,24 +199,26 @@ with gr.Blocks() as demo:
     background = gr.Textbox(label="Your background and field/goal")
     background_btn = gr.Button("Submit")
     background_output = gr.Textbox(label="Bot response", interactive=False)
-
     background_btn.click(save_background, inputs=[background, user_profile], outputs=[background_output, user_profile])
 
     gr.Markdown("### Step 3: Start Interview")
     chatbot = gr.Chatbot(label="Interview Bot")
-
     with gr.Row():
         msg = gr.Textbox(label="Your message")
         audio_input = gr.Audio(type="filepath", label="🎙️ Upload or Record your answer")
-
     with gr.Row():
         send_btn = gr.Button("Send Text")
         audio_btn = gr.Button("Send Audio")
-
-
     send_btn.click(respond, inputs=[msg, chat_history, user_profile], outputs=[chatbot], queue=False)
     send_btn.click(lambda: "", None, msg, queue=False)
     audio_btn.click(handle_audio, inputs=[audio_input, chat_history, user_profile], outputs=[chatbot], queue=False)
 
+    # ✅ Step 4: Webcam Posture Check
+    gr.Markdown("### Step 4: Webcam Posture Check")
+    webcam = gr.Image(source="webcam", type="pil", label="Capture Posture")
+    posture_output = gr.Textbox(label="Posture Feedback")
+    posture_btn = gr.Button("Analyze Posture")
+    posture_btn.click(classify_image, inputs=[webcam], outputs=[posture_output])
 
-demo.launch()
+# LAUNCH
+demo.launch()