app.py

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

# 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 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):
    prompt = f"The user said: {user_input}. Respond appropriately as a recruiter."
    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):
    """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?"

# Gradio interface
def mock_interview(audio, pdf):
    resume_embeddings = process_resume(pdf)
    transcription = stt_model(audio)["text"]
    question = generate_question(transcription, resume_embeddings)
    return transcription, question

interface = gr.Interface(
    fn=mock_interview,
    inputs=[gr.Audio(source="microphone", type="filepath"), gr.File(label="Upload Resume (PDF)")],
    outputs=["text", "text"],
    title="Mock Interview AI",
    description="Upload your resume and answer questions in a mock interview."
)

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