{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "mesCTyhnJkNS"
   },
   "source": [
    "# Prediction Guard\n",
    "\n",
    ">[Prediction Guard](https://docs.predictionguard.com/) gives a quick and easy access to state-of-the-art open and closed access LLMs, without  needing to spend days and weeks figuring out all of the implementation details, managing a bunch of different API specs, and setting up the infrastructure for model deployments."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "3RqWPav7AtKL"
   },
   "outputs": [],
   "source": [
    "! pip install predictionguard langchain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "2xe8JEUwA7_y"
   },
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import predictionguard as pg\n",
    "from langchain.llms import PredictionGuard\n",
    "from langchain import PromptTemplate, LLMChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "kp_Ymnx1SnDG"
   },
   "outputs": [],
   "source": [
    "# Optional, add your OpenAI API Key. This is optional, as Prediction Guard allows\n",
    "# you to access all the latest open access models (see https://docs.predictionguard.com)\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"<your OpenAI api key>\"\n",
    "\n",
    "# Your Prediction Guard API key. Get one at predictionguard.com\n",
    "os.environ[\"PREDICTIONGUARD_TOKEN\"] = \"<your Prediction Guard access token>\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "Ua7Mw1N4HcER"
   },
   "outputs": [],
   "source": [
    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "Qo2p5flLHxrB"
   },
   "outputs": [],
   "source": [
    "pgllm(\"Tell me a joke\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "EyBYaP_xTMXH"
   },
   "source": [
    "# Control the output structure/ type of LLMs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "55uxzhQSTPqF"
   },
   "outputs": [],
   "source": [
    "template = \"\"\"Respond to the following query based on the context.\n",
    "\n",
    "Context: EVERY comment, DM + email suggestion has led us to this EXCITING announcement! 🎉 We have officially added TWO new candle subscription box options! 📦\n",
    "Exclusive Candle Box - $80 \n",
    "Monthly Candle Box - $45 (NEW!)\n",
    "Scent of The Month Box - $28 (NEW!)\n",
    "Head to stories to get ALLL the deets on each box! 👆 BONUS: Save 50% on your first box with code 50OFF! 🎉\n",
    "\n",
    "Query: {query}\n",
    "\n",
    "Result: \"\"\"\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"query\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "yersskWbTaxU"
   },
   "outputs": [],
   "source": [
    "# Without \"guarding\" or controlling the output of the LLM.\n",
    "pgllm(prompt.format(query=\"What kind of post is this?\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "PzxSbYwqTm2w"
   },
   "outputs": [],
   "source": [
    "# With \"guarding\" or controlling the output of the LLM. See the \n",
    "# Prediction Guard docs (https://docs.predictionguard.com) to learn how to \n",
    "# control the output with integer, float, boolean, JSON, and other types and\n",
    "# structures.\n",
    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\", \n",
    "                        output={\n",
    "                                \"type\": \"categorical\",\n",
    "                                \"categories\": [\n",
    "                                    \"product announcement\", \n",
    "                                    \"apology\", \n",
    "                                    \"relational\"\n",
    "                                    ]\n",
    "                                })\n",
    "pgllm(prompt.format(query=\"What kind of post is this?\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "v3MzIUItJ8kV"
   },
   "source": [
    "# Chaining"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "pPegEZExILrT"
   },
   "outputs": [],
   "source": [
    "pgllm = PredictionGuard(model=\"OpenAI-text-davinci-003\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "suxw62y-J-bg"
   },
   "outputs": [],
   "source": [
    "template = \"\"\"Question: {question}\n",
    "\n",
    "Answer: Let's think step by step.\"\"\"\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
    "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
    "\n",
    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
    "\n",
    "llm_chain.predict(question=question)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "l2bc26KHKr7n"
   },
   "outputs": [],
   "source": [
    "template = \"\"\"Write a {adjective} poem about {subject}.\"\"\"\n",
    "prompt = PromptTemplate(template=template, input_variables=[\"adjective\", \"subject\"])\n",
    "llm_chain = LLMChain(prompt=prompt, llm=pgllm, verbose=True)\n",
    "\n",
    "llm_chain.predict(adjective=\"sad\", subject=\"ducks\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "I--eSa2PLGqq"
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}