import gradio as gr
import numpy as np
from transformers import pipeline
from sentence_transformers import SentenceTransformer
from sklearn.metrics.pairwise import cosine_similarity
import PyPDF2
import sounddevice as sd
import queue

# Load local models for inference
stt_model = pipeline("automatic-speech-recognition", model="openai/whisper-base")
conversation_model = pipeline("text-generation", model="facebook/blenderbot-400M-distill")

# Load a pre-trained model for vector embeddings
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')

# Parse PDF and create resume content
def parse_resume(pdf):
    """Extract text from an uploaded PDF file."""
    reader = PyPDF2.PdfReader(pdf)
    text = "\n".join(page.extract_text() for page in reader.pages if page.extract_text())
    sections = {"Resume Content": text}
    return sections

# Process job description text
def process_job_description(job_desc):
    """Encode the job description for analysis."""
    return embedding_model.encode(job_desc)

# Process resume and generate embeddings
def process_resume(pdf):
    resume_content = parse_resume(pdf)
    resume_embeddings = {
        section: embedding_model.encode(content) for section, content in resume_content.items()
    }
    return resume_embeddings

# Generate a conversation response
def generate_conversation_response(user_input, job_desc_embedding):
    prompt = f"The user said: {user_input}. Respond appropriately as a professional hiring manager. Focus on how the response relates to the job description."
    response = conversation_model(prompt, max_length=100, num_return_sequences=1)
    return response[0]["generated_text"]

# Generate question from user response
def generate_question(user_input, resume_embeddings, job_desc_embedding):
    """Find the most relevant section in the resume and generate a question."""
    user_embedding = embedding_model.encode(user_input)
    similarities = {
        section: cosine_similarity([user_embedding], [embedding])[0][0] 
        for section, embedding in resume_embeddings.items()
    }
    most_relevant_section = max(similarities, key=similarities.get)
    return f"Based on your experience in {most_relevant_section}, can you elaborate more?"

# Real-time audio recording and processing
def record_audio(callback):
    """Record audio and process it in real-time."""
    q = queue.Queue()

    def audio_callback(indata, frames, time, status):
        if status:
            print(status)
        q.put(indata.copy())

    with sd.InputStream(samplerate=16000, channels=1, callback=audio_callback):
        while True:
            audio_data = q.get()
            callback(audio_data)

# Gradio interface
class MockInterview:
    def __init__(self):
        self.resume_embeddings = None
        self.job_desc_embedding = None
        self.interview_active = False

    def upload_inputs(self, resume, job_desc):
        self.resume_embeddings = process_resume(resume)
        self.job_desc_embedding = process_job_description(job_desc)
        self.interview_active = True
        return "Resume and job description processed. Interview is starting."

    def conduct_interview(self, audio_data):
        if not self.interview_active:
            return "Please upload your resume and job description first.", ""

        transcription = stt_model(audio_data)["text"]  # Transcribe audio
        question = generate_question(transcription, self.resume_embeddings, self.job_desc_embedding)
        return transcription, question

    def end_interview(self):
        self.interview_active = False
        return "Interview ended. Thank you for participating."

mock_interview = MockInterview()

def upload_inputs(resume, job_desc):
    return mock_interview.upload_inputs(resume, job_desc)

def start_interview(audio_data_callback):
    """Start the interview automatically, processing audio in real-time."""
    if not mock_interview.interview_active:
        return "Please upload your resume and job description first."

    def process_audio(audio_data):
        transcription, question = mock_interview.conduct_interview(audio_data)
        audio_data_callback(transcription, question)

    record_audio(process_audio)

interface = gr.Blocks()
with interface:
    gr.Markdown("""# Mock Interview AI
Upload your resume and job description, then engage in a realistic interview simulation.""")

    with gr.Row():
        resume_input = gr.File(label="Upload Resume (PDF)")
        job_desc_input = gr.Textbox(label="Paste Job Description")
        upload_button = gr.Button("Upload and Start Interview")

    with gr.Row():
        transcription_output = gr.Textbox(label="Transcription")
        question_output = gr.Textbox(label="Question")
        end_button = gr.Button("End Interview")

    upload_button.click(upload_inputs, inputs=[resume_input, job_desc_input], outputs=[transcription_output])
    end_button.click(mock_interview.end_interview, outputs=[transcription_output])

if __name__ == "__main__":
    interface.launch()