{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Petals\n",
    "\n",
    "`Petals` runs 100B+ language models at home, BitTorrent-style.\n",
    "\n",
    "This notebook goes over how to use Langchain with [Petals](https://github.com/bigscience-workshop/petals)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Install petals\n",
    "The `petals` package is required to use the Petals API. Install `petals` using `pip3 install petals`.\n",
    "\n",
    "For Apple Silicon(M1/M2) users please follow this guide [https://github.com/bigscience-workshop/petals/issues/147#issuecomment-1365379642](https://github.com/bigscience-workshop/petals/issues/147#issuecomment-1365379642) to install petals "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip3 install petals"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from langchain.llms import Petals\n",
    "from langchain import PromptTemplate, LLMChain"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Set the Environment API Key\n",
    "Make sure to get [your API key](https://huggingface.co/docs/api-inference/quicktour#get-your-api-token) from Huggingface."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " ········\n"
     ]
    }
   ],
   "source": [
    "from getpass import getpass\n",
    "\n",
    "HUGGINGFACE_API_KEY = getpass()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ[\"HUGGINGFACE_API_KEY\"] = HUGGINGFACE_API_KEY"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create the Petals instance\n",
    "You can specify different parameters such as the model name, max new tokens, temperature, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Downloading:   1%|▏                        | 40.8M/7.19G [00:24<15:44, 7.57MB/s]"
     ]
    }
   ],
   "source": [
    "# this can take several minutes to download big files!\n",
    "\n",
    "llm = Petals(model_name=\"bigscience/bloom-petals\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create a Prompt Template\n",
    "We will create a prompt template for Question and Answer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "template = \"\"\"Question: {question}\n",
    "\n",
    "Answer: Let's think step by step.\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initiate the LLMChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run the LLMChain\n",
    "Provide a question and run the LLMChain."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
    "\n",
    "llm_chain.run(question)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.6"
  },
  "vscode": {
   "interpreter": {
    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}