Adding cookbook for using DALL-E from Azure OpenAI (#491)

* Add dalle notebook

* Fix

* Some small adjustments

* Smaller adjustments

* change flow of the notebook

* feedback

* more

* readme

* fixing typo

---------

Co-authored-by: Christian Mürtz <t-cmurtz@microsoft.com>
This commit is contained in:
Gerardo Lecaros 2023-06-12 14:01:49 -07:00 committed by GitHub
parent a49d153766
commit 70d089929f
2 changed files with 293 additions and 1 deletions

View File

@ -53,6 +53,7 @@ Most code examples are written in Python, though the concepts can be applied in
- [How to use ChatGPT with Azure OpenAI](examples/azure/chat.ipynb) - [How to use ChatGPT with Azure OpenAI](examples/azure/chat.ipynb)
- [How to get completions from Azure OpenAI](examples/azure/completions.ipynb) - [How to get completions from Azure OpenAI](examples/azure/completions.ipynb)
- [How to get embeddings from Azure OpenAI](examples/azure/embeddings.ipynb) - [How to get embeddings from Azure OpenAI](examples/azure/embeddings.ipynb)
- [How to generate images with DALL·E fom Azure OpenAI](examples/azure/DALL-E.ipynb)
## Related OpenAI resources ## Related OpenAI resources

291
examples/azure/DALL-E.ipynb Normal file
View File

@ -0,0 +1,291 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"# Azure DALL·E image generation example\n",
"\n",
"This notebook shows how to generate images with the Azure OpenAI service."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"## Setup\n",
"\n",
"First, we install the necessary dependencies."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"! pip install openai\n",
"# We need requests to retrieve the generated image\n",
"! pip install requests\n",
"# We use Pillow to display the generated image\n",
"! pip install pillow \n",
"# (Optional) If you want to use Microsoft Active Directory\n",
"! pip install azure-identity"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import openai"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Additionally, to properly access the Azure OpenAI Service, we need to create the proper resources at the [Azure Portal](https://portal.azure.com) (you can check a detailed guide on how to do this in the [Microsoft Docs](https://learn.microsoft.com/en-us/azure/cognitive-services/openai/how-to/create-resource?pivots=web-portal))\n",
"\n",
"Once the resource is created, the first thing we need to use is its endpoint. You can get the endpoint by looking at the *\"Keys and Endpoints\"* section under the *\"Resource Management\"* section. Having this, we will set up the SDK using this information:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"openai.api_base = '' # Add your endpoint here\n",
"\n",
"# At the moment DALL·E is only supported by the 2023-06-01-preview API version\n",
"openai.api_version = '2023-06-01-preview'"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Authentication\n",
"\n",
"The Azure OpenAI service supports multiple authentication mechanisms that include API keys and Azure credentials."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"use_azure_active_directory = False"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"#### Authentication using API key\n",
"\n",
"To set up the OpenAI SDK to use an *Azure API Key*, we need to set up the `api_type` to `azure` and set `api_key` to a key associated with your endpoint (you can find this key in *\"Keys and Endpoints\"* under *\"Resource Management\"* in the [Azure Portal](https://portal.azure.com))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"if not use_azure_active_directory:\n",
" openai.api_type = 'azure'\n",
" openai.api_key = '' # Add your api key here"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Authentication using Microsoft Active Directory\n",
"Let's now see how we can get a key via Microsoft Active Directory Authentication."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from azure.identity import DefaultAzureCredential\n",
"\n",
"if use_azure_active_directory:\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",
"\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",
"if use_azure_active_directory:\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": [
"## Generations\n",
"\n",
"With setup and authentication complete, you can now generate images on the Azure OpenAI service and retrieve them from the returned URLs."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 1. Generate the images\n",
"\n",
"The first step in this process is to actually generate the images:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"generation_response = openai.Image.create(\n",
" prompt='A cyberpunk monkey hacker dreaming of a beautiful bunch of bananas, digital art',\n",
" size='1024x1024',\n",
" n=2\n",
")\n",
"\n",
"print(generation_response)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"Having the response from the `Image.create` call, we download from the URL using `requests`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"import requests\n",
"\n",
"# First a little setup\n",
"image_dir = os.path.join(os.curdir, 'images')\n",
"# If the directory doesn't exist, create it\n",
"if not os.path.isdir(image_dir):\n",
" os.mkdir(image_dir)\n",
"\n",
"# With the directory in place, we can initialize the image path (note that filetype should be png)\n",
"image_path = os.path.join(image_dir, 'generated_image.png')\n",
"\n",
"# Now we can retrieve the generated image\n",
"image_url = generation_response[\"data\"][0][\"url\"] # extract image URL from response\n",
"generated_image = requests.get(image_url).content # download the image\n",
"with open(image_path, \"wb\") as image_file:\n",
" image_file.write(generated_image)"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"With the image downloaded, we use the [Pillow](https://pypi.org/project/Pillow/) library to open and display it:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from PIL import Image \n",
"\n",
"display(Image.open(image_path))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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
}