quick_start/v1/07_prompt_engineering.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "import requests\n",
    "import sys\n",
    "import os\n",
    "from openai import AzureOpenAI\n",
    "import tiktoken\n",
    "from dotenv import load_dotenv\n",
    "load_dotenv()\n",
    "\n",
    "client = AzureOpenAI(\n",
    "  azure_endpoint = os.getenv(\"AZURE_OPENAI_ENDPOINT\"), \n",
    "  api_key=os.getenv(\"AZURE_OPENAI_KEY\"),  \n",
    "  api_version=\"2024-02-15-preview\"\n",
    ")\n",
    "\n",
    "CHAT_COMPLETIONS_MODEL = os.getenv('AZURE_OPENAI_DEPLOYMENT_NAME')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# A Few Shot Learning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "😍,👏,✨\n"
     ]
    }
   ],
   "source": [
    "# Zero-shot classification\n",
    "system_prompt =\"\"\"Predict up to 5 emojis as a response to a text chat message. The output\n",
    "should only include emojis.\n",
    "\n",
    "input: The new visual design is blowing my mind 🤯\n",
    "output: ➕,💘, ❤‍🔥\n",
    "\n",
    "input: Well that looks great regardless\n",
    "output: ❤️,🪄\n",
    "\n",
    "input: Unfortunately this won't work\n",
    "output: 💔,😔\n",
    "\n",
    "input: sounds good, I'll look into that\n",
    "output: 🙏,👍\n",
    "\n",
    "input: 10hr cut of jeff goldblum laughing URL\n",
    "output: 😂,💀,⚰️\n",
    "\"\"\"\n",
    "user_prompt = \"The new user interface is amazing!\"\n",
    "response = client.chat.completions.create(\n",
    "    model=CHAT_COMPLETIONS_MODEL,\n",
    "    messages = [{\"role\":\"system\", \"content\":system_prompt},\n",
    "                {\"role\":\"user\",\"content\": user_prompt,}])\n",
    "print(response.choices[0].message.content)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Prompt Engineering Best Practices\n",
    "\n",
    "## Write clear instructions\n",
    "\n",
    "Examples:\n",
    "\n",
    "-----------------------\n",
    "Prompt:\n",
    "\n",
    "Write code to calculate the Fibonacci sequence.\n",
    "\n",
    "Better:\n",
    "\n",
    "Write a TypeScript function to efficiently calculate the Fibonacci sequence. Comment the code liberally to explain what each piece does and why it's written that way.\n",
    "\n",
    "----------------------\n",
    "\n",
    "Prompt:\n",
    "\n",
    "Summarize the meeting notes.\n",
    "\n",
    "Better:\n",
    "\n",
    "Summarize the meeting notes in a single paragraph. Then write a markdown list of the speakers and each of their key points. Finally, list the next steps or action items suggested by the speakers, if any.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Role Playing\n",
    "\n",
    "Examples:\n",
    "\n",
    "-----------------------\n",
    "\n",
    "System Message: When I ask for help to write something, you will reply with a document that contains at least one joke or playful comment in every paragraph.\n",
    "\n",
    "----------------------\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Segment input text\n",
    "\n",
    "Examples:\n",
    "\n",
    "------------------------\n",
    "\n",
    "user message: Summarize the text delimited by triple quotes with a haiku.\n",
    "\n",
    "\"\"\"insert text here\"\"\"\n",
    "\n",
    "------------------------\n",
    "\n",
    "system message: You will be provided with a pair of articles (delimited with XML tags) about the same topic. First summarize the arguments of each article. Then indicate which of them makes a better argument and explain why.\n",
    "\n",
    "user message: \n",
    "\n",
    "\\<article> insert first article here \\</article>\n",
    "\n",
    "\\<article> insert second article here \\</article>\n",
    "\n",
    "------------------------"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Explain steps and processes to complete a task\n",
    "\n",
    "Examples:\n",
    "\n",
    "--------------------------------\n",
    "\n",
    "System Message:\n",
    "Use the following step-by-step instructions to respond to user inputs.\n",
    "\n",
    "Step 1 - The user will provide you with text in triple quotes. Summarize this text in one sentence with a prefix that says \"Summary: \".\n",
    "\n",
    "Step 2 - Translate the summary from Step 1 into Spanish, with a prefix that says \"Translation: \".\n",
    "\n",
    "---------------------------------"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Use few-shot learning\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": []
  }
 ],
 "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": "3.12.5"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}