import openai
import gradio as gr
import os
# Set your OpenAI API key here


openai.api_key = os.environ.get("openai_api_key")

# Define a function to generate responses using GPT-3.5 Turbo
def generate_response(user_prompt):

    # Define the system message
    system_msg = 'You are a helpful assistant.'

# Define the user message
    prompt= f'''I will give you a question and you detect which category does this question belong to. It should be from these categories - 
        physical activity, sleep, nutrition and preventive care. Make sure you just reply with response in json format "category":"[sleep,nutrition]". 
        Note that single question may belong to multiple categories. Dont add any opening lines just reply with json response. If there is no match return no category
        Question: {user_prompt}'''
    #user_msg = 'Create a small dataset about total sales over the last year. The format of the dataset should be a data frame with 12 rows and 2 columns. The columns should be called "month" and "total_sales_usd". The "month" column should contain the shortened forms of month names from "Jan" to "Dec". The "total_sales_usd" column should contain random numeric values taken from a normal distribution with mean 100000 and standard deviation 5000. Provide Python code to generate the dataset, then provide the output in the format of a markdown table.'

# Create a dataset using GPT
   
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",  # Use GPT-3.5 Turbo engine,
        messages=[{"role": "system", "content": system_msg},
                                         {"role": "user", "content": prompt}],
        max_tokens=100,  # You can adjust this to limit the response length
    )
    return response["choices"][0]["message"]["content"]

# Create a Gradio interface

iface = gr.Interface(fn=generate_response,
                     inputs=[gr.components.Textbox( label="prompt",
                                                   value='Who is the target population for Abdominal Aortic Aneurysm (AAA) screening?')],
                     outputs=[gr.JSON(label="category")]
                    )

# Start the Gradio interface
iface.launch()