app.py

import gradio as gr
import os
import json


from google import genai
from google.genai import types

import math
import types
import uuid


MODEL_ID = "gemini-2.0-flash-exp"
from google import genai
client = genai.Client(api_key=os.getenv('api_g_key'))

def llm_response(text):
  response = client.models.generate_content(
    model=MODEL_ID,
    contents= text)
  return response.text

# Collect functions from `math` built-in

def aiq(problem):
    critic_answer = llm_response(f'''You are an expert AI career advisor and skills evaluator. You are also a very harsh critic who is more interested in objective facts and speaking truth rather than sugarcoating stuff. Your task is to analyze the following resume and compute a highly objective AI Quotient (AIQ) Score on a scale of 0 to 100.

The AI Quotient reflects the candidate's readiness to understand, apply, and innovate with AI technologies in practical environments.

Scoring Framework:

Break down the total score into five categories, each contributing 20 points to the total 100-point scale:

Foundational AI Knowledge (0-20 points)
Assess formal education (courses, certifications) in AI, ML, data science, statistics, mathematics, or computer science.
Score higher for advanced degrees or top-tier certifications (e.g., Coursera Deep Learning Specialization, Google Cloud ML Engineer).
Practical AI Project Experience (0-20 points)
Evaluate hands-on projects, open-source contributions, hackathons, or work experience directly involving AI or ML.
Score higher for production-grade projects, end-to-end model lifecycle experience, or leadership in AI projects.
Tooling and Technical Proficiency (0-20 points)
Evaluate the use of AI-relevant tools and technologies: Python, TensorFlow, PyTorch, scikit-learn, OpenAI APIs, Google Cloud AI, etc.
Bonus points for familiarity with prompt engineering, LangChain, RAG architectures, or advanced deployment skills (Docker, Kubernetes).
AI Thought Leadership and Community Involvement (0-20 points)
Assess public speaking, blogging, publishing papers, conducting workshops, contributing to AI forums, or active GitHub repos related to AI.
Score higher for community leadership, meetups, or recognized speaking engagements.
Continuous Learning and Future Readiness (0-20 points)
Check for evidence of recent AI upskilling (past 12 months): courses, certifications, recent project work, or AI experiments.
Score higher for consistent learning habits and future-oriented skills (multimodal AI, autonomous agents, LLM fine-tuning).
Final Output Format:

AI Quotient Score: X/100
Breakdown:

Foundational Knowledge: X/20
Practical AI Projects: X/20
Tools & Tech Stack: X/20
AI Community Involvement: X/20
Continuous Learning: X/20
Key Observations:

(Provide 2-3 strengths and weaknesses based on the resume)
3-Step Roadmap to Improve AI Quotient: Do not provide hyperlinks.

(Most impactful next step)
(Complementary project or certification)
(Community engagement or advanced topic exploration)
Resume:

"""
{problem}
"""''')
    
    return critic_answer
                                      

iface = gr.Interface(
    fn=aiq, 
    inputs=gr.TextArea(label="Copy/paste your resume)"), 
    outputs=gr.Markdown(label="Your AI Quotient"),  # Output as HTML
    title="AI Quotient",
    description="AI Quotient (AIQ) is an emerging measure of an individual’s readiness to understand, apply, and leverage artificial intelligence in professional and creative contexts. Just as IQ measures cognitive reasoning or EQ measures emotional intelligence, AIQ quantifies a person’s practical capability to thrive in an AI-powered world.",
    theme = gr.themes.Ocean()
        )

# Launch the app
iface.launch()