import requests
import json

# Define a sample business utility function: Book Tickets
def book_tickets():
    """
    Sample business utility function to demonstrate booking tickets.

    Replace this with your actual booking tickets logic.
    """
    print("Booking Tickets...")
    # Your booking tickets logic here
    print("Tickets Booked Successfully.")

# Define a sample business utility function: Pay Bills
def pay_bills():
    """
    Sample business utility function to demonstrate paying bills.

    Replace this with your actual bill payment logic.
    """
    print("Paying Bills...")
    # Your bill payment logic here
    print("Bills Paid Successfully.")

# Define a function to execute your business-utility functions
def execute_function(function_name):
    """
    Executes a user-defined business utility function by its name if it exists in the global scope.

    Args:
        function_name (str): The name of the business utility function to be executed.

    Returns:
        None
    """
    if function_name in globals() and callable(globals()[function_name]):
        globals()[function_name]()
    else:
        print(f"Business utility function '{function_name}' not found or not callable.")

# Define a function to extract adjusted similarity values and related content
def extract_adjusted_similarity_values(s):
    """
    Extracts adjusted similarity values and related business content from a string.

    Args:
        s (str): The input string containing adjusted similarity values and business content.

    Returns:
        list: A list of dictionaries containing adjusted similarity and business content.
    """
    results = []
    start = 0
    while True:
        start = s.find('"adjusted_similarity":', start)
        if start == -1:
            break
        start_value = start + len('"adjusted_similarity":')
        end_value = s.find(',', start_value)
        adjusted_similarity = float(s[start_value:end_value].strip())

        start_output = s.find('"output":"', end_value) + len('"output":"')
        end_output = s.find('"}', start_output) if s[start_output - 2] != ']' else s.find('"}]', start_output)
        output = s[start_output:end_output].strip()

        results.append({"adjusted_similarity": adjusted_similarity, "business_content": output})
        start = end_value

    return results

# Specify the id of your trained transformer
transformer_id = "2"
# Action can either be PrefrontalCortex or Amygdala
action = "PrefrontalCortex"
user_message = input("Enter your message: ")
print("You entered:", user_message)

# Construct the conversation array
conversation = [
    {"content": "You are a really helpful assistant", "role": "system"},
    {"content": "Hey there, how can I assist you today?", "role": "assistant"},
    {"content": user_message, "role": "user"}
]

# Prepare the request body
request_body = {
    "conversation": conversation,
    "action": action,
    "transformer_id": transformer_id
}

# Endpoint URL
url = "https://ai.wiom.in/process_rgwai"

# Make the POST request
response = requests.post(url, json=request_body)

# Process and print the modified response
modified_response = response.text.replace('\\', '')
if modified_response.startswith('"') and modified_response.endswith('"'):
    modified_response = modified_response[1:-1]

# Extract Amygdala and Prefrontal Cortex results
start_amygdala = modified_response.find('"amygdala_result":"') + len('"amygdala_result":"')
end_amygdala = modified_response.find(']"', start_amygdala) + 1
amygdala_result_raw = modified_response[start_amygdala:end_amygdala]

start_prefrontal = modified_response.find('"prefrontal_cortex_result":"') + len('"prefrontal_cortex_result":"')
end_prefrontal = modified_response.find('}"', start_prefrontal) + 1
prefrontal_cortex_result_raw = modified_response[start_prefrontal:end_prefrontal]

# Process Amygdala results and execute relevant business actions
amygdala_result = json.loads(amygdala_result_raw)
for result in amygdala_result:
    if result["adjusted_similarity"] > 60.0:
        function_name = result["output"]
        print(f"Amygdala Adjusted Similarity: {result['adjusted_similarity']}", f"Business Action: {function_name}")
        print()
        execute_function(function_name)

# Process Prefrontal Cortex results
extracted_results = extract_adjusted_similarity_values(prefrontal_cortex_result_raw)

# Find the item with the highest adjusted similarity
highest_similarity_item = max(extracted_results, key=lambda x: x["adjusted_similarity"])
print()

# Print the adjusted similarity and business content with the highest relevance
print("Highest Adjusted Similarity:", highest_similarity_item["adjusted_similarity"])
print("Relevant Business Content:", highest_similarity_item["business_content"])

# What next? ... depending on business requirements, you can choose to use Amygdala and Prefrontal Cortex results in isolation or cumulatively, and even make their usage contingent on a minimum similarity score.

            
          

              

import requests

# File paths
training_data_file_path = 'path/to/your/training_data.csv'
vpfc_globals_file_path = 'path/to/your/vpfc_globals.csv'
url = 'https://ai.wiom.in/transform_transformer'

# Open the files in binary mode
with open(training_data_file_path, 'rb') as training_data, \
     open(vpfc_globals_file_path, 'rb') as vpfc_globals:

    # Create a dictionary of files
    files = {
        'training_data': training_data,
        'vpfc_globals': vpfc_globals
    }

    # Send the POST request
    response = requests.post(url, files=files)

    # Print the response
    print("Status Code:", response.status_code)
    print("Response Body:", response.text)