app.py

pip install openai

import streamlit as st
import openai

# Initialize the OpenAI API
openai.api_key = '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'

KNOWN_MODELS = [
    "Neural Networks", "Decision Trees", "Support Vector Machines", 
    "Random Forests", "Linear Regression", "Reinforcement Learning"
]

def recommend_ai_model_via_gpt(description):
    # Formulate a prompt for the large language model
    prompt = f"Given the application described as: '{description}', which AI model would be most suitable?"

    response = openai.Completion.create(
        model="gpt-4.0-turbo",
        prompt=prompt,
        max_tokens=50
    )
    
    recommendation = response.choices[0].text.strip()
    return recommendation

def explain_recommendation(model_name):
    # Formulate a prompt for explanation
    prompt = f"Why would {model_name} be a suitable choice for the application?"

    response = openai.Completion.create(
        model="gpt-4.0-turbo",
        prompt=prompt,
        max_tokens=150
    )
    
    explanation = response.choices[0].text.strip()
    return explanation

def get_feedback():
    feedback = input("Was this recommendation helpful? (yes/no): ").lower()
    if feedback == 'yes':
        print("Thank you for your feedback!")
    else:
        print("Thank you! We'll strive to improve.")

def rate_explanation():
    try:
        rating = int(input("Rate the explanation from 1 (worst) to 5 (best): "))
        if 1 <= rating <= 5:
            print("Thank you for rating!")
        else:
            print("Invalid rating. Please rate between 1 and 5.")
    except ValueError:
        print("Invalid input. Please enter a number between 1 and 5.")


# Streamlit UI
st.title('AI Model Recommender')

description = st.text_area("Describe your application:", "")
if st.button("Recommend AI Model"):
    if description:
        recommended_model = recommend_ai_model_via_gpt(description)
        
        # Validate recommended model
        if recommended_model not in KNOWN_MODELS:
            st.warning("The recommendation is ambiguous. Please refine your description or consult an expert.")
        else:
            st.subheader(f"Recommended AI Model: {recommended_model}")
            explanation = explain_recommendation(recommended_model)
            st.write("Reason:", explanation)

            # Collecting rating and feedback through Streamlit
            rating = st.slider("Rate the explanation from 1 (worst) to 5 (best):", 1, 5)
            feedback = st.text_input("Any additional feedback?")

            if st.button("Submit Feedback"):
                st.success("Thank you for your feedback!")
    else:
        st.warning("Please provide a description.")