{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Chatbot Development\n",
    "\n",
    "Use this notebook to load the model and then initialize, update, and test the chatbot."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Setup and Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch\n",
    "from huggingface_hub import login\n",
    "\n",
    "\n",
    "from src.chat import SchoolChatbot\n",
    "from config import BASE_MODEL, MY_MODEL"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "TODO: Add your Hugging Face token\n",
    "Options:\n",
    "1. Use login() and enter token when prompted. It won't ask for your token if you already logged in using the command: huggingface-cli login in the terminal.\n",
    "2. Set environment variable HUGGINGFACE_TOKEN\n",
    "3. Pass token directly (not recommended for shared notebooks)\n",
    "\"\"\"\n",
    "\n",
    "login()\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Initialize and test chatbot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Create chatbot instance using chat.py\n",
    "\"\"\"\n",
    "chatbot = SchoolChatbot()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"\"\"\n",
    "Test out generating some responses from the chatbot.\n",
    "Inference time\n",
    "\"\"\"\n",
    "test_question = \"I live in Jamaica Plain and want to send my child to a school that offers Spanish classes. What schools are available?\"\n",
    "\n",
    "print(f\"\\nQuestion: {test_question}\")\n",
    "response = chatbot.get_response(test_question)\n",
    "print(f\"Response: {response}\")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# TODO: Update pre-trained Llama to be a school choice chatbot\n",
    "\n",
    "This part is up to you! You might want to finetune the model, simply make a really good system prompt, use RAG, provide the model boston school choice data in-context, etc. Be creative!\n",
    "\n",
    "You can also feel free to do this in another script and then evaluate the model here.\n",
    "\n",
    "Tips:\n",
    "- HuggingFace has built-in methods to finetune models, if you choose that route. Take advantage of those methods! You can then save your new, finetuned model in the HuggingFace Hub. Change MY_MODEL in config.py to the name of the model in the hub to make your chatbot use it.\n",
    "- You may also want to consider LoRA if you choose finetuning."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "venv",
   "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}