{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#| hide\n",
    "from lv_recipe_chatbot import app"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# lv-recipe-chatbot\n",
    "\n",
    "> An experimental Vegan recipe chatbot"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This file will become your README and also the index of your documentation."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Install"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "```sh\n",
    "pip install lv_recipe_chatbot\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## How to use"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "load_dotenv() # or load environment vars with different method\n",
    "\n",
    "app.create_demo(app.ConversationBot())\n",
    "app.launch()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "or \n",
    "```sh\n",
    "python3 app.py\n",
    "```"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Dev quick-start\n",
    "\n",
    "`git clone` the repo  \n",
    "\n",
    "```sh\n",
    "cd lv-recipe-chatbot\n",
    "```  \n",
    "\n",
    "Make sure to use the version of python specified in `py_version.txt`  \n",
    "Create a virtual environment.\n",
    "\n",
    "```sh\n",
    "python3 -m venv env\n",
    "```\n",
    "\n",
    "Activate the env and install dependencies.\n",
    "\n",
    "```sh\n",
    "source env/bin/activate\n",
    "pip install -r requirements.txt\n",
    "pip install -r requirements/dev.txt\n",
    "```\n",
    "\n",
    "To make the Jupyter environment, git friendly: `nbdev_install_hooks`  \n",
    "If you want to render documentation locally, you will want to [install Quarto](https://nbdev.fast.ai/tutorials/tutorial.html#install-quarto).\n",
    "\n",
    "`nbdev_install_quarto` \n",
    "\n",
    "Put API secrets in .env\n",
    "\n",
    "```sh\n",
    "cp .env.example .env\n",
    "```\n",
    "\n",
    "Edit .env with your secret key(s). Only `OPEN_AI_KEY` is required.\n",
    "\n",
    "Then start the Gradio demo from within the virtual environment.  \n",
    "\n",
    "```sh\n",
    "python3 app.py\n",
    "```\n",
    "\n",
    "Preview documentation\n",
    "\n",
    "```sh\n",
    "nbdev_preview\n",
    "```\n",
    "\n",
    "## Dependencies\n",
    "\n",
    "If a new dependency for development is helpful for developers, add it to `dev.txt`.  \n",
    "If it is a dependency for the app that is imported in source code, add it to `core.txt`.  \n",
    "Then run:\n",
    "\n",
    "```sh\n",
    "pipreqs --force\n",
    "```\n",
    "\n",
    "This will update our `requirements.txt` to include the dependency as it should be pinned in the environment.  \n",
    "\n",
    "\n",
    "## Development\n",
    "\n",
    "[quick nbdev tutorial](https://nbdev.fast.ai/tutorials)\n",
    "\n",
    "Make changes in `/nbs`.  \n",
    "Update the package files with `nbdev_export` then reimport with `pip install -e '.[dev]'`\n",
    "\n",
    "Preview doc `nbdev_preview`  \n",
    "Build docs, test and update README `nbdev_prepare`\n",
    "\n",
    "\n",
    "\n",
    "## Useful links\n",
    "\n",
    "* [Task Matrix (Formerly Visual ChatGPT)](https://github.com/microsoft/TaskMatrix)\n",
    "* [LangChain](https://python.langchain.com/en/latest/index.html)\n",
    "* [LLM Prompt Engineering](https://www.promptingguide.ai)\n",
    "* [OpenAI best practices for prompts](https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "python3",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}