{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import Required Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from dotenv import load_dotenv\n",
    "from openai import OpenAI\n",
    "import gradio as gr "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Load Environment Variables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {},
   "outputs": [],
   "source": [
    "load_dotenv()\n",
    "openai_api_key = os.getenv('OPENAI_API_KEY')\n",
    "if not openai_api_key:\n",
    "    print(\"OpenAI API Key not set\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Initialize OpenAI Client and Define Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {},
   "outputs": [],
   "source": [
    "openai = OpenAI()\n",
    "MODEL = 'gpt-4o-mini'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the System Message"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [],
   "source": [
    "system_message = (\n",
    "    \"You are a helpful assistant, trying your best to answer every question as accurately as possible. \"\n",
    "    \"You are also free to say you do not know if you do not have the information to answer a question. \"\n",
    "    \"You always respond in markdown.\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define the Chat Function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {},
   "outputs": [],
   "source": [
    "def chat(message, history):\n",
    "    messages = [{\"role\": \"system\", \"content\": system_message}] + history + [{\"role\": \"user\", \"content\": message}]\n",
    "\n",
    "    stream = openai.chat.completions.create(model=MODEL, messages=messages, stream=True)\n",
    "\n",
    "    response = \"\"\n",
    "    for chunk in stream:\n",
    "        response += chunk.choices[0].delta.content or ''\n",
    "        yield response"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create the Chat Interface"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {},
   "outputs": [],
   "source": [
    "demo = gr.ChatInterface(\n",
    "    fn=chat,\n",
    "    title=\"AI chatbot\",\n",
    "    description=\"Please login to use the chat interface\",\n",
    "    type='messages',\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "auth_data is a list of tuples, where each tuple contains a username and password."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [],
   "source": [
    "auth_data = [(\"user_1\", \"password_1\"), (\"user_2\", \"password_2\"), (\"user_3\", \"password_3\")]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Add Authentication and Launch\n",
    "\n",
    "auth_message is the message displayed to users before accessing the interface."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "demo.launch(share=True,\n",
    "    auth=auth_data,\n",
    "    auth_message=\"Please enter your credentials to access the chat interface\",\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llms",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}