Update app.py

app.py

@@ -1,22 +1,89 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import re
 
+# ---- Load and parse questions from knowledge.txt ----
+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:
+        parts = block.split('Possible Answers:')
+        question_text = parts[0].strip()
+        answers_text = parts[1].strip()
+        possible_answers = [ans.strip() for ans in re.split(r'\d+\.\s+', answers_text) if ans.strip()]
+        questions.append({'question': question_text, 'answers': possible_answers})
+    return questions
+
+all_questions = load_questions('knowledge.txt')
+
+# ---- Simple way to assign questions to interview types ----
+# You can replace this later with better tagging
+questions_by_type = {
+    'Technical': [q for q in all_questions if any(keyword in q['question'].lower() for keyword in ['function', 'algorithm', 'sql', 'system', 'java', 'programming', 'data', 'design', 'api', 'distributed', 'garbage', 'hash', 'stack', 'bfs', 'dfs'])],
+    'Behavioral': [q for q in all_questions if any(keyword in q['question'].lower() for keyword in ['tell me about a time', 'describe a situation', 'example of', 'negotiation', 'lead', 'mistake', 'stakeholder'])],
+    'College': []  # For now keep empty unless you add questions for this
+}
+
+# ---- Hugging Face Client ----
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# ---- Interview type selection ----
 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
 
+# ---- Save background ----
 def save_background(info, user_profile):
     user_profile["field"] = info
     return "Awesome! Type 'start' below to begin your interview.", user_profile
 
+# ---- Main respond logic ----
 def respond(message, chat_history, user_profile):
     if not user_profile.get("interview_type") or not user_profile.get("field"):
         bot_msg = "Please finish steps 1 and 2 before starting the interview."
         chat_history.append((message, bot_msg))
         return chat_history
 
+    # Start interview logic
+    if message.strip().lower() == 'start':
+        interview_type = user_profile['interview_type']
+        selected_questions = questions_by_type.get(interview_type, [])
+        user_profile['questions'] = selected_questions
+        user_profile['current_q'] = 0
+        user_profile['user_answers'] = []
+        if not selected_questions:
+            bot_msg = "No questions available for this interview type."
+        else:
+            bot_msg = f"First question: {selected_questions[0]['question']}"
+        chat_history.append((message, bot_msg))
+        return chat_history
+
+    # If interview is ongoing
+    if user_profile.get("questions"):
+        q_index = user_profile['current_q']
+        user_profile['user_answers'].append(message)
+
+        q_index += 1
+        user_profile['current_q'] = q_index
+
+        if q_index < len(user_profile['questions']):
+            bot_msg = f"Next question: {user_profile['questions'][q_index]['question']}"
+        else:
+            bot_msg = "Interview complete! Type 'feedback' if you'd like me to analyze your answers."
+        chat_history.append((message, bot_msg))
+        return chat_history
+
+    # Handle feedback request
+    if message.strip().lower() == 'feedback':
+        feedback = generate_feedback(user_profile)
+        chat_history.append((message, feedback))
+        return chat_history
+
+    # Default fallback
     messages = [
         {"role": "system", "content": f"You are a professional interviewer conducting a {user_profile['interview_type']} interview for a candidate in the {user_profile['field']} field."}
     ]
@@ -30,13 +97,29 @@ def respond(message, chat_history, user_profile):
     chat_history.append((message, bot_msg))
     return chat_history
 
+# ---- Simple feedback function (keyword based for now) ----
+def generate_feedback(user_profile):
+    feedback = []
+    questions = user_profile.get('questions', [])
+    answers = user_profile.get('user_answers', [])
+
+    for i, user_ans in enumerate(answers):
+        correct_answers = questions[i]['answers']
+        match = any(ans.lower() in user_ans.lower() for ans in correct_answers)
+        if match:
+            fb = f"Question {i+1}: ✅ Good job! You covered key points."
+        else:
+            fb = f"Question {i+1}: ❌ You missed some key points: {correct_answers[0]}"
+        feedback.append(fb)
+    return "\n".join(feedback)
+
+# ---- Gradio Interface ----
 with gr.Blocks() as demo:
     user_profile = gr.State({"interview_type": "", "field": ""})
     chat_history = gr.State([])
 
     gr.Markdown("# 🎤 Welcome to Intervu")
 
-    # Step 1
     gr.Markdown("### Step 1: Choose Interview Type")
     with gr.Row():
         with gr.Column():
@@ -49,7 +132,6 @@ with gr.Blocks() as demo:
     btn2.click(set_type, inputs=[gr.Textbox(value="Technical", visible=False), user_profile], outputs=[type_output, user_profile])
     btn3.click(set_type, inputs=[gr.Textbox(value="College", visible=False), user_profile], outputs=[type_output, user_profile])
 
-    # Step 2
     gr.Markdown("### Step 2: Enter Your Background")
     background = gr.Textbox(label="Your background and field/goal")
     background_btn = gr.Button("Submit")
@@ -57,7 +139,6 @@ with gr.Blocks() as demo:
 
     background_btn.click(save_background, inputs=[background, user_profile], outputs=[background_output, user_profile])
 
-    # Step 3
     gr.Markdown("### Step 3: Start Interview")
     chatbot = gr.Chatbot(label="Interview Bot")
     msg = gr.Textbox(label="Your message")
@@ -67,3 +148,4 @@ with gr.Blocks() as demo:
     send_btn.click(lambda: "", None, msg, queue=False)
 
 demo.launch()
+