Update app.py

app.py

@@ -1,130 +1,115 @@
 import gradio as gr
 import requests
 import os
-import random
 import re
 
+# We use Mistral because DialoGPT is for chatting, while Mistral follows instructions
+API_URL = "https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.3"
 HF_TOKEN = os.getenv("HF_TOKEN")
 
-API_URL = "https://api-inference.huggingface.co/models/microsoft/DialoGPT-medium"
-
-headers = {
-    "Authorization": f"Bearer {HF_TOKEN}"
-}
-
-# ----------------------------
-# AI Question Generator
-# ----------------------------
-def generate_question(role, difficulty, resume_text):
-    base_prompt = f"Generate one {difficulty} level technical interview question for a {role} role."
-
-    if resume_text.strip() != "":
-        base_prompt += f" The candidate resume mentions: {resume_text}. Ask a question based on that."
+headers = {"Authorization": f"Bearer {HF_TOKEN}"}
 
+def query_llm(prompt):
+    """Helper function to send prompts to the Hugging Face API."""
     payload = {
-        "inputs": base_prompt,
-        "parameters": {"max_new_tokens": 100}
+        "inputs": f"<s>[INST] {prompt} [/INST]",
+        "parameters": {"max_new_tokens": 250, "temperature": 0.7}
     }
-
-    response = requests.post(API_URL, headers=headers, json=payload)
-
-    if response.status_code != 200:
-        return "Error generating question."
-
-    result = response.json()
-
-    if isinstance(result, list):
-        return result[0]["generated_text"]
-
-    return "Could not generate question."
-
+    try:
+        response = requests.post(API_URL, headers=headers, json=payload)
+        result = response.json()
+        
+        if isinstance(result, list) and "generated_text" in result[0]:
+            # Clean the output to remove the prompt markers
+            full_text = result[0]["generated_text"]
+            return full_text.split("[/INST]")[-1].strip()
+        
+        return "The AI is still warming up. Please wait 30 seconds and try again."
+    except Exception as e:
+        return f"Error: Could not connect to AI (Check your HF_TOKEN). {str(e)}"
 
 # ----------------------------
-# AI Answer Evaluation + Score
+# AI Logic Functions
 # ----------------------------
-def evaluate_answer(answer):
-    feedback_prompt = f"""
-    Evaluate this interview answer.
-    Give:
-    1. Short feedback
-    2. Score out of 10
 
-    Answer: {answer}
+def generate_question(role, difficulty, resume_text):
+    if not role:
+        return "Please enter a Job Role first!"
+        
+    prompt = f"Act as a professional recruiter. Generate one {difficulty} level technical interview question for a {role} role."
+    if resume_text.strip():
+        prompt += f" Based on this resume context: {resume_text}"
+    
+    return query_llm(prompt)
+
+def evaluate_answer(question, answer):
+    if not answer or len(answer) < 5:
+        return "Please provide a more detailed answer for evaluation.", "N/A"
+        
+    prompt = f"""
+    Interviewer Question: {question}
+    Candidate Answer: {answer}
+    
+    Task: Critically evaluate this answer. 
+    1. Give constructive feedback.
+    2. Provide a score out of 10.
+    Format your response with the score clearly at the end as 'Final Score: X/10'.
     """
-
-    payload = {
-        "inputs": feedback_prompt,
-        "parameters": {"max_new_tokens": 150}
-    }
-
-    response = requests.post(API_URL, headers=headers, json=payload)
-
-    if response.status_code != 200:
-        return "Error generating feedback.", "0/10"
-
-    result = response.json()
-
-    if isinstance(result, list):
-        text = result[0]["generated_text"]
-
-        # Try extracting score
-        score_match = re.search(r"\b([0-9]|10)/10\b", text)
-        score = score_match.group(0) if score_match else "N/A"
-
-        return text, score
-
-    return "Could not evaluate.", "0/10"
-
+    
+    feedback = query_llm(prompt)
+    
+    # Extract score using regex (looks for X/10)
+    score_match = re.search(r"(\d+/10)", feedback)
+    score = score_match.group(1) if score_match else "Score not generated"
+    
+    return feedback, score
 
 # ----------------------------
-# Gradio UI
+# Gradio UI Design
 # ----------------------------
-with gr.Blocks() as demo:
-    gr.Markdown("# 🤖 Smart Interview Simulator (AI Voice Bot)")
-    gr.Markdown("AI-powered role-based interview practice with scoring and resume-based questions.")
-
-    with gr.Row():
-        role = gr.Textbox(label="Job Role (e.g., Data Scientist)")
-        difficulty = gr.Dropdown(
-            ["Easy", "Medium", "Hard"],
-            label="Select Difficulty",
-            value="Medium"
-        )
-
-    resume_input = gr.Textbox(
-        label="Paste Resume Skills / Summary (Optional)",
-        lines=4
-    )
-
-    question_output = gr.Textbox(label="Interview Question", lines=3)
-
-    generate_btn = gr.Button("Generate Question")
 
-    gr.Markdown("## 🎤 Answer Section")
-
-    audio_input = gr.Audio(
-        sources=["microphone"],
-        type="filepath",
-        label="Speak Your Answer (Voice Input)"
-    )
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🤖 Smart Interview Simulator")
+    gr.Markdown("Practice your interview skills with AI-generated questions and real-time feedback.")
 
-    answer_input = gr.Textbox(label="OR Type Your Answer", lines=4)
-
-    evaluate_btn = gr.Button("Evaluate Answer")
+    with gr.Row():
+        with gr.Column():
+            role_input = gr.Textbox(label="Target Job Role", placeholder="e.g., Python Developer")
+            diff_input = gr.Dropdown(["Easy", "Medium", "Hard"], label="Level", value="Medium")
+            resume_input = gr.Textbox(label="Resume Summary (Optional)", lines=3)
+            gen_btn = gr.Button("Generate Interview Question", variant="primary")
+        
+        with gr.Column():
+            question_box = gr.Textbox(label="AI Question", lines=5, interactive=False)
 
-    feedback_output = gr.Textbox(label="AI Feedback", lines=5)
-    score_output = gr.Textbox(label="Score")
+    gr.Markdown("---")
 
-    generate_btn.click(
-        generate_question,
-        inputs=[role, difficulty, resume_input],
-        outputs=question_output
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### Your Response")
+            # Note: For voice input to work, Gradio handles the file, 
+            # but you would need a transcription model (like Whisper) to convert audio to text.
+            # For now, we will focus on the text input.
+            ans_input = gr.Textbox(label="Type your answer here", lines=5)
+            eval_btn = gr.Button("Submit for Evaluation", variant="secondary")
+            
+        with gr.Column():
+            gr.Markdown("### Results")
+            feedback_box = gr.Textbox(label="AI Feedback", lines=5)
+            score_box = gr.Label(label="Final Score")
+
+    # Button actions
+    gen_btn.click(
+        fn=generate_question, 
+        inputs=[role_input, diff_input, resume_input], 
+        outputs=question_box
     )
-
-    evaluate_btn.click(
-        evaluate_answer,
-        inputs=answer_input,
-        outputs=[feedback_output, score_output]
+    
+    eval_btn.click(
+        fn=evaluate_answer, 
+        inputs=[question_box, ans_input], 
+        outputs=[feedback_box, score_box]
     )
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()