Add zero shot prompting example

examples/prompting/Zero_shot_prompting.ipynb

@@ -0,0 +1,216 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Gemini API: Zero-shot prompting"
+      ],
+      "metadata": {
+        "id": "sP8PQnz1QrcF"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "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/quickstarts/examples/prompting/Zero_shot_prompting.ipynb\"><img src = \"https://www.tensorflow.org/images/colab_logo_32px.png\"/>Run in Google Colab</a>\n",
+        "  </td>\n",
+        "</table>"
+      ],
+      "metadata": {
+        "id": "bxGr_x3MRA0z"
+      }
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "Because of the vast knowledge of Gemini 1.5 Pro model, it can answer many queries without any additional context. Zero-shot prompting is useful for situations when our queries are not complicated and do not require a specific schema."
+      ],
+      "metadata": {
+        "id": "ysy--KfNRrCq"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install -U -q google-generativeai"
+      ],
+      "metadata": {
+        "id": "Ne-3gnXqR0hI"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "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",
+      "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."
+      ],
+      "metadata": {
+        "id": "eomJzCa6lb90"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from google.colab import userdata\n",
+        "GOOGLE_API_KEY=userdata.get('GOOGLE_API_KEY')\n",
+        "\n",
+        "genai.configure(api_key=GOOGLE_API_KEY)"
+      ],
+      "metadata": {
+        "id": "v-JZzORUpVR2"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "## Examples\n",
+        "\n",
+        "Here are a few examples with zero-shot prompting. Note that in each of these examples, we just provide the task, with zero examples."
+      ],
+      "metadata": {
+        "id": "GLh4oXd1VXTw"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "model = genai.GenerativeModel('gemini-pro', generation_config={\"temperature\": 0})"
+      ],
+      "metadata": {
+        "id": "Ym4w9z3iWHlT"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "prompt = \"\"\"\n",
+        "Sort following animals from biggest to smallest:\n",
+        "fish, elephant, dog\n",
+        "\"\"\"\n",
+        "Markdown(model.generate_content(prompt).text)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 97
+        },
+        "id": "J580DkQPVYYp",
+        "outputId": "0435e167-4cad-4c9a-ab60-369031d54dbd"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.Markdown object>"
+            ],
+            "text/markdown": "1. Elephant\n2. Dog\n3. Fish"
+          },
+          "metadata": {},
+          "execution_count": 5
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "prompt = \"\"\"\n",
+        "classify sentiment of review as positive, negative or neutral:\n",
+        "I go to this restaurant every week, i love it so much.\n",
+        "\"\"\"\n",
+        "Markdown(model.generate_content(prompt).text)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 46
+        },
+        "id": "K1we-_q4VZ0M",
+        "outputId": "3e8d7583-fe5b-4ca9-9b4c-4756ae80e86a"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.Markdown object>"
+            ],
+            "text/markdown": "positive"
+          },
+          "metadata": {},
+          "execution_count": 6
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "prompt = \"\"\"\n",
+        "extract capital cities from the text:\n",
+        "During the summer I visited many countries in Europe. First I visited Italy, specifically Sicily and Rome. Then I visited Cologne in Germany and the trip ended in Berlin.\n",
+        "\"\"\"\n",
+        "Markdown(model.generate_content(prompt).text)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 64
+        },
+        "id": "4NF2OmfPVa4l",
+        "outputId": "dbf599f6-68d7-4c00-86ce-5267dcf13d57"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.Markdown object>"
+            ],
+            "text/markdown": "- Rome\n- Berlin"
+          },
+          "metadata": {},
+          "execution_count": 7
+        }
+      ]
+    }
+  ]
+}