Update app.py

app.py

@@ -3,187 +3,66 @@ import requests
 import os
 import random
 
-# =====================================
-# CONFIG
-# =====================================
-
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-WHISPER_API = "https://api-inference.huggingface.co/models/openai/whisper-base"
-LLM_API = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2"
+API_URL = "https://api-inference.huggingface.co/models/microsoft/DialoGPT-medium"
 
 headers = {
     "Authorization": f"Bearer {HF_TOKEN}"
 }
 
-# =====================================
-# Question Bank
-# =====================================
-
-questions = {
-    "Easy": [
-        "What is Machine Learning?",
-        "Explain supervised learning.",
-        "What is overfitting?"
-    ],
-    "Medium": [
-        "Explain bias vs variance tradeoff.",
-        "What is gradient descent?",
-        "Difference between CNN and RNN?"
-    ],
-    "Hard": [
-        "Explain backpropagation.",
-        "What is attention mechanism?",
-        "Explain transformer architecture."
-    ]
-}
-
-# =====================================
-# Generate Question
-# =====================================
-
-def start_interview(level):
-    return random.choice(questions[level])
-
-# =====================================
-# Speech-to-Text using API
-# =====================================
-
-def speech_to_text(audio_path):
-    try:
-        with open(audio_path, "rb") as f:
-            audio_bytes = f.read()
-
-        response = requests.post(
-            WHISPER_API,
-            headers=headers,
-            data=audio_bytes
-        )
-
-        if response.status_code == 200:
-            return response.json().get("text", "Could not transcribe audio.")
-        else:
-            return "Speech recognition API error."
-
-    except Exception as e:
-        return f"Speech recognition failed: {str(e)}"
-
-
-# =====================================
-# LLM Evaluation
-# =====================================
-
-def evaluate_with_llm(question, answer):
-
-    prompt = f"""
-You are a strict technical interviewer.
-
-Question:
-{question}
-
-Candidate Answer:
-{answer}
-
-Evaluate and give:
-
-1. Technical Accuracy (0-10)
-2. Clarity (0-10)
-3. Depth (0-10)
-4. Overall Score (0-10)
-5. Improvement Suggestions
-
-Be concise and structured.
-"""
-
+def generate_question(role):
+    prompt = f"Generate one technical interview question for a {role} role."
+    
     payload = {
         "inputs": prompt,
-        "parameters": {
-            "max_new_tokens": 300,
-            "temperature": 0.7
-        }
+        "parameters": {"max_new_tokens": 80}
     }
 
-    try:
-        response = requests.post(
-            LLM_API,
-            headers=headers,
-            json=payload
-        )
-
-        if response.status_code == 200:
-            return response.json()[0]["generated_text"]
-        else:
-            return "LLM evaluation API error."
-
-    except Exception as e:
-        return f"Evaluation failed: {str(e)}"
-
-
-# =====================================
-# Main Evaluation Function
-# =====================================
-
-def evaluate_answer(audio, question):
-
-    if audio is None:
-        return "Please record your answer."
-
-    if question.strip() == "":
-        return "Please click 'Start Interview' first."
-
-    transcribed_text = speech_to_text(audio)
+    response = requests.post(API_URL, headers=headers, json=payload)
+    
+    if response.status_code != 200:
+        return "Error generating question. Check your HF_TOKEN."
+
+    result = response.json()
+    
+    if isinstance(result, list):
+        return result[0]["generated_text"]
+    
+    return "Could not generate question."
+
+def evaluate_answer(answer):
+    feedback_prompt = f"Evaluate this interview answer and give short feedback:\nAnswer: {answer}"
+    
+    payload = {
+        "inputs": feedback_prompt,
+        "parameters": {"max_new_tokens": 120}
+    }
 
-    feedback = evaluate_with_llm(question, transcribed_text)
+    response = requests.post(API_URL, headers=headers, json=payload)
 
-    return f"""
-📝 Transcribed Answer:
-{transcribed_text}
+    if response.status_code != 200:
+        return "Error generating feedback."
 
-📊 Evaluation:
-{feedback}
-"""
+    result = response.json()
 
+    if isinstance(result, list):
+        return result[0]["generated_text"]
 
-# =====================================
-# UI
-# =====================================
+    return "Could not evaluate answer."
 
 with gr.Blocks() as demo:
-
-    gr.Markdown("# 🎤 Smart Interview Simulator")
-    gr.Markdown("Voice-Based AI Mock Interview System")
-
-    level_dropdown = gr.Dropdown(
-        ["Easy", "Medium", "Hard"],
-        value="Medium",
-        label="Select Difficulty"
-    )
-
+    gr.Markdown("# 🤖 Smart Interview Simulator (AI Voice Bot)")
+    
+    role = gr.Textbox(label="Enter Job Role (e.g., Data Scientist)")
     question_output = gr.Textbox(label="Interview Question")
+    answer_input = gr.Textbox(label="Your Answer")
+    feedback_output = gr.Textbox(label="AI Feedback")
+
+    generate_btn = gr.Button("Generate Question")
+    evaluate_btn = gr.Button("Evaluate Answer")
 
-    start_button = gr.Button("Start Interview")
-    start_button.click(
-        start_interview,
-        inputs=level_dropdown,
-        outputs=question_output
-    )
-
-    audio_input = gr.Audio(
-        type="filepath",
-        label="Record Your Answer"
-    )
-
-    submit_button = gr.Button("Submit Answer")
-
-    result_output = gr.Textbox(
-        label="Evaluation Feedback",
-        lines=15
-    )
-
-    submit_button.click(
-        evaluate_answer,
-        inputs=[audio_input, question_output],
-        outputs=result_output
-    )
+    generate_btn.click(generate_question, inputs=role, outputs=question_output)
+    evaluate_btn.click(evaluate_answer, inputs=answer_input, outputs=feedback_output)
 
 demo.launch()