{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Azure embeddings example\n",
    "\n",
    "> Note: There is a newer version of the openai library available. See https://github.com/openai/openai-python/discussions/742\n",
    "\n",
    "This example will cover embeddings using the Azure OpenAI service."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First, we install the necessary dependencies."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "! pip install \"openai>=0.28.1,<1.0.0\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For the following sections to work properly we first have to setup some things. Let's start with the `api_base` and `api_version`. To find your `api_base` go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for the \"Endpoint\" value."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import openai"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "openai.api_version = '2023-05-15'\n",
    "openai.api_base = '' # Please add your endpoint here"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We next have to setup the `api_type` and `api_key`. We can either get the key from the portal or we can get it through Microsoft Active Directory Authentication. Depending on this the `api_type` is either `azure` or `azure_ad`."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Setup: Portal\n",
    "Let's first look at getting the key from the portal. Go to https://portal.azure.com, find your resource and then under \"Resource Management\" -> \"Keys and Endpoints\" look for one of the \"Keys\" values."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "openai.api_type = 'azure'\n",
    "openai.api_key = os.environ[\"OPENAI_API_KEY\"]"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "> Note: In this example, we configured the library to use the Azure API by setting the variables in code. For development, consider setting the environment variables instead:\n",
    "\n",
    "```\n",
    "OPENAI_API_BASE\n",
    "OPENAI_API_KEY\n",
    "OPENAI_API_TYPE\n",
    "OPENAI_API_VERSION\n",
    "```"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### (Optional) Setup: Microsoft Active Directory Authentication\n",
    "Let's now see how we can get a key via Microsoft Active Directory Authentication. Uncomment the following code if you want to use Active Directory Authentication instead of keys from the portal."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# from azure.identity import DefaultAzureCredential\n",
    "\n",
    "# default_credential = DefaultAzureCredential()\n",
    "# token = default_credential.get_token(\"https://cognitiveservices.azure.com/.default\")\n",
    "\n",
    "# openai.api_type = 'azure_ad'\n",
    "# openai.api_key = token.token"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "A token is valid for a period of time, after which it will expire. To ensure a valid token is sent with every request, you can refresh an expiring token by hooking into requests.auth:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import typing\n",
    "import time\n",
    "import requests\n",
    "if typing.TYPE_CHECKING:\n",
    "    from azure.core.credentials import TokenCredential\n",
    "\n",
    "class TokenRefresh(requests.auth.AuthBase):\n",
    "\n",
    "    def __init__(self, credential: \"TokenCredential\", scopes: typing.List[str]) -> None:\n",
    "        self.credential = credential\n",
    "        self.scopes = scopes\n",
    "        self.cached_token: typing.Optional[str] = None\n",
    "\n",
    "    def __call__(self, req):\n",
    "        if not self.cached_token or self.cached_token.expires_on - time.time() < 300:\n",
    "            self.cached_token = self.credential.get_token(*self.scopes)\n",
    "        req.headers[\"Authorization\"] = f\"Bearer {self.cached_token.token}\"\n",
    "        return req\n",
    "\n",
    "session = requests.Session()\n",
    "session.auth = TokenRefresh(default_credential, [\"https://cognitiveservices.azure.com/.default\"])\n",
    "\n",
    "openai.requestssession = session"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Deployments\n",
    "In this section we are going to create a deployment that we can use to create embeddings."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Deployments: Create manually\n",
    "Let's create a deployment using the `text-similarity-curie-001` model. Create a new deployment by going to your Resource in your portal under \"Resource Management\" -> \"Model deployments\"."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "deployment_id = '' # Fill in the deployment id from the portal here"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Deployments: Listing\n",
    "Now because creating a new deployment takes a long time, let's look in the subscription for an already finished deployment that succeeded."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print('While deployment running, selecting a completed one that supports embeddings.')\n",
    "deployment_id = None\n",
    "result = openai.Deployment.list()\n",
    "for deployment in result.data:\n",
    "    if deployment[\"status\"] != \"succeeded\":\n",
    "        continue\n",
    "    \n",
    "    model = openai.Model.retrieve(deployment[\"model\"])\n",
    "    if model[\"capabilities\"][\"embeddings\"] != True:\n",
    "        continue\n",
    "    \n",
    "    deployment_id = deployment[\"id\"]\n",
    "    break\n",
    "\n",
    "if not deployment_id:\n",
    "    print('No deployment with status: succeeded found.')\n",
    "else:\n",
    "    print(f'Found a succeeded deployment that supports embeddings with id: {deployment_id}.')"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Embeddings\n",
    "Now let's send a sample embedding to the deployment."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = openai.Embedding.create(deployment_id=deployment_id,\n",
    "                                     input=\"The food was delicious and the waiter...\")\n",
    "                                \n",
    "print(embeddings)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.11.3"
  },
  "vscode": {
   "interpreter": {
    "hash": "3a5103089ab7e7c666b279eeded403fcec76de49a40685dbdfe9f9c78ad97c17"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}