add chain of thought prompting example

examples/prompting/Chain_of_thought_prompting.ipynb

@@ -0,0 +1,223 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fzRFGWxAsTm2"
+      },
+      "source": [
+        "##### Copyright 2024 Google LLC."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "Y0nQsAf2sSfs"
+      },
+      "outputs": [],
+      "source": [
+        "# @title Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "# https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "sP8PQnz1QrcF"
+      },
+      "source": [
+        "# Gemini API: Chain of thought prompting"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bxGr_x3MRA0z"
+      },
+      "source": [
+        "<table class=\"tfo-notebook-buttons\" align=\"left\">\n",
+        "  <td>\n",
+        "    <a target=\"_blank\" href=\"https://colab.research.google.com/github/google-gemini/cookbook/blob/main/examples/prompting/Chain_of_thought_prompting.ipynb\"><img src = \"https://www.tensorflow.org/images/colab_logo_32px.png\"/>Run in Google Colab</a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ysy--KfNRrCq"
+      },
+      "source": [
+        "Using chain of thought helps the LLM take a logical and arithmetic approach. Instead of outputting the answer immediately, the LLM uses smaller and easier steps to get to the answer."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Ne-3gnXqR0hI"
+      },
+      "outputs": [],
+      "source": [
+        "!pip install -U -q google-generativeai"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "EconMHePQHGw"
+      },
+      "outputs": [],
+      "source": [
+        "import google.generativeai as genai\n",
+        "\n",
+        "from IPython.display import Markdown"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "eomJzCa6lb90"
+      },
+      "source": [
+        "## Configure your API key\n",
+        "\n",
+        "To run the following cell, your API key must be stored it in a Colab Secret named `GOOGLE_API_KEY`. If you don't already have an API key, or you're not sure how to create a Colab Secret, see [Authentication](https://github.com/google-gemini/cookbook/blob/main/quickstarts/Authentication.ipynb) for an example."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "v-JZzORUpVR2"
+      },
+      "outputs": [],
+      "source": [
+        "from google.colab import userdata\n",
+        "GOOGLE_API_KEY=userdata.get('GOOGLE_API_KEY')\n",
+        "\n",
+        "genai.configure(api_key=GOOGLE_API_KEY)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "LlRYq9JSeRzR"
+      },
+      "source": [
+        "## Example\n",
+        "\n",
+        "Here is an example with chain of thought prompting. Take a look at what the result would be without chain of thought implemented."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8oS9LnnXXedG"
+      },
+      "outputs": [],
+      "source": [
+        "model = genai.GenerativeModel(model_name='gemini-1.5-flash-latest', generation_config={\"temperature\": 0})"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0u1IjBOmeQgG"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/markdown": "Here's how to solve this problem:\n\n**Understanding the Relationship**\n\n* **People and Donuts:** If 5 people make 5 donuts, that means each person makes 1 donut in 5 minutes.\n* **Time:**  The time it takes to make a donut doesn't change with more people.\n\n**Solving the Problem**\n\n1. **Individual Rate:** Each person makes 1 donut every 5 minutes.\n2. **Total Donuts:** With 25 people, they can make 25 donuts every 5 minutes (25 people * 1 donut/person = 25 donuts).\n3. **Time for 100 Donuts:** To make 100 donuts, it would take 20 minutes (100 donuts / 25 donuts/5 minutes = 20 minutes).\n\n**Answer:** It would take 25 people **20 minutes** to make 100 donuts. \n",
+            "text/plain": [
+              "<IPython.core.display.Markdown object>"
+            ]
+          },
+          "execution_count": 8,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "prompt = \"\"\"\n",
+        "Q: 5 people can create 5 donuts every 5 minutes. How much time would it take 25 people to make 100 donuts?\n",
+        "A:\"\"\"\n",
+        "Markdown(model.generate_content(prompt).text)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "kCFJ2dvBubSm"
+      },
+      "source": [
+        "Now, implement chain of thought into your prompt and look at the difference in the response. Note the multiple steps implemented within the prompt."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "HdMNHASyeWoK"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/markdown": "Here's how to solve this problem:\n\n**1. Find the individual production rate:**\n\n* 5 people make 5 donuts in 5 minutes, meaning one person makes 1 donut in 5 minutes.\n\n**2. Calculate the total production rate with 25 people:**\n\n* With 25 people, they can make 25 donuts every 5 minutes (25 people * 1 donut/person/5 minutes = 25 donuts/5 minutes).\n\n**3. Determine the time to make 100 donuts:**\n\n* Since they make 25 donuts every 5 minutes, they make 5 sets of 25 donuts in 25 minutes (5 sets * 5 minutes/set = 25 minutes).\n\n**Answer:** It would take 25 people **25 minutes** to make 100 donuts. \n",
+            "text/plain": [
+              "<IPython.core.display.Markdown object>"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "prompt = \"\"\"\n",
+        "Q: 11 factories can make 22 cars per hour. How much time would it take 22 factories to make 88 cars?\n",
+        "A: A factory can make 22/11=2 cars per hour. 22 factories can make 22*2=44 cars per hour. Making 88 cars would take 88/44=2 hours. The answer is 2 hours.\n",
+        "Q: 5 people can create 5 donuts every 5 minutes. How much time would it take 25 people to make 100 donuts?\n",
+        "A:\"\"\"\n",
+        "Markdown(model.generate_content(prompt).text)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "w_K9Sn3Yu9eL"
+      },
+      "source": [
+        "## Next steps\n",
+        "\n",
+        "Be sure to explore other examples of prompting in the repository. Try writing prompts about classifying your own data, or try some of the other prompting techniques such as few-shot prompting."
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "Chain_of_thought_prompting.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}