# Import the necessary functions from ollama, Flask, requests, threading
from ollama import Client
from flask import Flask, request, jsonify
#import requests
#import threading

# Initialize a Flask application
app = Flask(__name__)

def get_response(user_query):
  # Create a client object for interacting with OLLAMA API
    client = Client()

    # Generate and retrieve the response based on user's query
    response = client.generate_response(user_query)

    # Return the generated response
    return response

def run_flask():
    # Flask endpoint for user interaction
    app.run(port=5000, debug=True)



@app.route('/smartassist', methods=['POST'])
def smartassist():
    # Extract the query from the incoming JSON data
    data = request.json
    user_query = data['query']

    # Get the response from the OLLAMA API based on the user's query
    # NOTE: Should we append message history here? Maybe interact with SQLlite?
    response = get_response(user_query)

    # Return the response as a JSON object in the HTTP response
    return jsonify({"response": response})


@app.route('/api/chat', methods=['POST'])
def chat():
    data = request.get_json()
    query = data['query']
    response = requests.post('http://ollama-server/api/v1/chat', json={'prompt': query})
    return jsonify({'response': response.json().get('result')})


if __name__ == '__main__':
    # Run the Flask application
    run_flask()