|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "# Azure embeddings example\n", |
| 8 | + "In this example we'll try to go over all operations for embeddings that can be done using the Azure endpoints. \\\n", |
| 9 | + "This example focuses on finetuning but touches on the majority of operations that are also available using the API. This example is meant to be a quick way of showing simple operations and is not meant as a tutorial." |
| 10 | + ] |
| 11 | + }, |
| 12 | + { |
| 13 | + "cell_type": "code", |
| 14 | + "execution_count": null, |
| 15 | + "metadata": {}, |
| 16 | + "outputs": [], |
| 17 | + "source": [ |
| 18 | + "import openai\n", |
| 19 | + "from openai import cli" |
| 20 | + ] |
| 21 | + }, |
| 22 | + { |
| 23 | + "cell_type": "markdown", |
| 24 | + "metadata": {}, |
| 25 | + "source": [ |
| 26 | + "## Setup\n", |
| 27 | + "In the following section the endpoint and key need to be set up of the next sections to work. \\\n", |
| 28 | + "Please go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value and one of the Keys. They will act as api_base and api_key in the code below." |
| 29 | + ] |
| 30 | + }, |
| 31 | + { |
| 32 | + "cell_type": "code", |
| 33 | + "execution_count": null, |
| 34 | + "metadata": {}, |
| 35 | + "outputs": [], |
| 36 | + "source": [ |
| 37 | + "openai.api_key = '' # Please add your api key here\n", |
| 38 | + "openai.api_base = '' # Please add your endpoint here\n", |
| 39 | + "\n", |
| 40 | + "openai.api_type = 'azure'\n", |
| 41 | + "openai.api_version = '2022-03-01-preview' # this may change in the future" |
| 42 | + ] |
| 43 | + }, |
| 44 | + { |
| 45 | + "cell_type": "markdown", |
| 46 | + "metadata": {}, |
| 47 | + "source": [ |
| 48 | + "## Deployments\n", |
| 49 | + "In this section we are going to create a deployment using the finetune model that we just adapted and then used the deployment to create a simple completion operation." |
| 50 | + ] |
| 51 | + }, |
| 52 | + { |
| 53 | + "cell_type": "markdown", |
| 54 | + "metadata": {}, |
| 55 | + "source": [ |
| 56 | + "### Deployments: Create Manually\n", |
| 57 | + "Let's create a deployment using the text-similarity-curie-001 engine. You can create a new deployment by going to your Resource in your portal under \"Resource Management\" -> \"Deployments\"." |
| 58 | + ] |
| 59 | + }, |
| 60 | + { |
| 61 | + "cell_type": "markdown", |
| 62 | + "metadata": {}, |
| 63 | + "source": [ |
| 64 | + "### (Optional) Deployments: Create Programatically\n", |
| 65 | + "We can also create a deployment using code:" |
| 66 | + ] |
| 67 | + }, |
| 68 | + { |
| 69 | + "cell_type": "code", |
| 70 | + "execution_count": null, |
| 71 | + "metadata": {}, |
| 72 | + "outputs": [], |
| 73 | + "source": [ |
| 74 | + "model = \"text-similarity-curie-001\"\n", |
| 75 | + "\n", |
| 76 | + "# Now let's create the deployment\n", |
| 77 | + "print(f'Creating a new deployment with model: {model}')\n", |
| 78 | + "result = openai.Deployment.create(model=model, scale_settings={\"scale_type\":\"manual\", \"capacity\": 1})\n", |
| 79 | + "deployment_id = result[\"id\"]" |
| 80 | + ] |
| 81 | + }, |
| 82 | + { |
| 83 | + "cell_type": "markdown", |
| 84 | + "metadata": {}, |
| 85 | + "source": [ |
| 86 | + "### (Optional) Deployments: Retrieving\n", |
| 87 | + "Now let's check the status of the newly created deployment" |
| 88 | + ] |
| 89 | + }, |
| 90 | + { |
| 91 | + "cell_type": "code", |
| 92 | + "execution_count": null, |
| 93 | + "metadata": {}, |
| 94 | + "outputs": [], |
| 95 | + "source": [ |
| 96 | + "print(f'Checking for deployment status.')\n", |
| 97 | + "resp = openai.Deployment.retrieve(id=deployment_id)\n", |
| 98 | + "status = resp[\"status\"]\n", |
| 99 | + "print(f'Deployment {deployment_id} is with status: {status}')" |
| 100 | + ] |
| 101 | + }, |
| 102 | + { |
| 103 | + "cell_type": "markdown", |
| 104 | + "metadata": {}, |
| 105 | + "source": [ |
| 106 | + "### Deployments: Listing\n", |
| 107 | + "Now because creating a new deployment takes a long time, let's look in the subscription for an already finished deployment that succeeded." |
| 108 | + ] |
| 109 | + }, |
| 110 | + { |
| 111 | + "cell_type": "code", |
| 112 | + "execution_count": null, |
| 113 | + "metadata": {}, |
| 114 | + "outputs": [], |
| 115 | + "source": [ |
| 116 | + "print('While deployment running, selecting a completed one.')\n", |
| 117 | + "deployment_id = None\n", |
| 118 | + "result = openai.Deployment.list()\n", |
| 119 | + "for deployment in result.data:\n", |
| 120 | + " if deployment[\"status\"] == \"succeeded\":\n", |
| 121 | + " deployment_id = deployment[\"id\"]\n", |
| 122 | + " break\n", |
| 123 | + "\n", |
| 124 | + "if not deployment_id:\n", |
| 125 | + " print('No deployment with status: succeeded found.')\n", |
| 126 | + "else:\n", |
| 127 | + " print(f'Found a successful deployment with id: {deployment_id}.')" |
| 128 | + ] |
| 129 | + }, |
| 130 | + { |
| 131 | + "cell_type": "markdown", |
| 132 | + "metadata": {}, |
| 133 | + "source": [ |
| 134 | + "### Embeddings\n", |
| 135 | + "Now let's send a sample embedding to the deployment." |
| 136 | + ] |
| 137 | + }, |
| 138 | + { |
| 139 | + "cell_type": "code", |
| 140 | + "execution_count": null, |
| 141 | + "metadata": {}, |
| 142 | + "outputs": [], |
| 143 | + "source": [ |
| 144 | + "embeddings = openai.Embedding.create(engine=deployment_id,\n", |
| 145 | + " input=\"The food was delicious and the waiter...\")\n", |
| 146 | + " \n", |
| 147 | + "print(embeddings)" |
| 148 | + ] |
| 149 | + }, |
| 150 | + { |
| 151 | + "cell_type": "markdown", |
| 152 | + "metadata": {}, |
| 153 | + "source": [ |
| 154 | + "### (Optional) Deployments: Delete\n", |
| 155 | + "Finally let's delete the deployment" |
| 156 | + ] |
| 157 | + }, |
| 158 | + { |
| 159 | + "cell_type": "code", |
| 160 | + "execution_count": null, |
| 161 | + "metadata": {}, |
| 162 | + "outputs": [], |
| 163 | + "source": [ |
| 164 | + "print(f'Deleting deployment: {deployment_id}')\n", |
| 165 | + "openai.Deployment.delete(sid=deployment_id)" |
| 166 | + ] |
| 167 | + } |
| 168 | + ], |
| 169 | + "metadata": { |
| 170 | + "interpreter": { |
| 171 | + "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6" |
| 172 | + }, |
| 173 | + "kernelspec": { |
| 174 | + "display_name": "Python 3.8.10 64-bit", |
| 175 | + "language": "python", |
| 176 | + "name": "python3" |
| 177 | + }, |
| 178 | + "language_info": { |
| 179 | + "codemirror_mode": { |
| 180 | + "name": "ipython", |
| 181 | + "version": 3 |
| 182 | + }, |
| 183 | + "file_extension": ".py", |
| 184 | + "mimetype": "text/x-python", |
| 185 | + "name": "python", |
| 186 | + "nbconvert_exporter": "python", |
| 187 | + "pygments_lexer": "ipython3", |
| 188 | + "version": "3.8.10" |
| 189 | + }, |
| 190 | + "orig_nbformat": 4 |
| 191 | + }, |
| 192 | + "nbformat": 4, |
| 193 | + "nbformat_minor": 2 |
| 194 | +} |
0 commit comments