Azure OpenAI Service Component

Interact with OpenAI models, including Chat GPT and DALL·E

Component key: azure-openai-service

Description

OpenAI is an artificial intelligence research laboratory that conducts AI research. It has notably produced the chat AI ChatGPT and the image generator DALL·E.

This component wraps some of OpenAI's REST API endpoints. Additional endpoints can be referenced in their API documentation. You can use the Raw Request action to interact with endpoints that are not covered by other actions.

Connections

OpenAI API Key

If you'd like to use an Azure OpenAI resource, you must have an Azure subscription and Azure OpenAI access. This will allow you to create an Azure OpenAI resource and get both a connection URL as well as API keys. For more information, see Quickstart: Get started generating text using Azure OpenAI Service.

Integrations can authenticate with OpenAI using API keys or Microsoft Entra Tokens:

To generate an API key from OpenAI:

1. Navigate toplatform.openai.com/account/api-keys and generate a new key. a. If your user is associate with one organization, you can leave the connection's organization field blank. Otherwise, specify your organization's ID.

To generate a token using Microsoft Entra authentication refer to the following authentication with Microsoft Entra ID guide for detailed prerequisites and configuration.

If you'd like to use the Azure OpenAI JS client library to connect to non-Azure OpenAI, you'll need an API key from a developer account at https://platform.openai.com/.

Input	Notes	Example
API Key	This API KEY Generate an API key at https://platform.openai.com/account/api-keys or your Azure OpenAI API KEY.
Is OpenAI Key	Set to true if this api key belongs to an OpenAI account.
Organization	Your Azure OpenAI organization. If using a OpenAI API KEY, this is not required.	my-account

Actions

Create Chat Completion

Create a completion for the chat message | key: createChatCompletion

Input	Notes	Example
Connection
Messages
Model / Deployment Name	Specifies either the model deployment name (when using Azure OpenAI) or model name (when using non-Azure OpenAI) to use for this request.	gpt-3.5-turbo
Number of choices	How many chat completion choices to generate for each input message.	1
Temperature	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.	1
top_p	An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.	1

---

Create Image

Create image(s) given a prompt | key: createImage

Input	Notes	Example
Connection
Image Size	The size of the generated images. Must be one of 1792x1024, 1024x1792, or 1024x1024.	1024x1024
Number of Images	The number of images to generate. Must be between 1 and 10.	1
Prompt	A text description of the desired image(s). The maximum length is 1000 characters.	A cute baby sea otter

{
  "data": [
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    }
  ]
}

---

Create Multiple Chat Completion

Generate Multiple Completions | key: createCompletions

Input	Notes	Example
Connection
Messages
Model / Deployment Name	Specifies either the model deployment name (when using Azure OpenAI) or model name (when using non-Azure OpenAI) to use for this request.	gpt-3.5-turbo

---

Raw Request

Send raw HTTP request to Azure OpenAI | key: rawRequest

Input	Notes	Example
Connection
Data	The HTTP body payload to send to the URL.	{"exampleKey": "Example Data"}
Debug Request	Enabling this flag will log out the current request.	false
File Data	File Data to be sent as a multipart form upload.	[{key: "example.txt", value: "My File Contents"}]
File Data File Names	File names to apply to the file data inputs. Keys must match the file data keys above.
Form Data	The Form Data to be sent as a multipart form upload.	[{"key": "Example Key", "value": new Buffer("Hello World")}]
Header	A list of headers to send with the request.	User-Agent: curl/7.64.1
Max Retry Count	The maximum number of retries to attempt.	0
Method	The HTTP method to use.
Query Parameter	A list of query parameters to send with the request. This is the portion at the end of the URL similar to ?key1=value1&key2=value2.
Response Type	The type of data you expect in the response. You can request json, text, or binary data.	json
Retry On All Errors	If true, retries on all erroneous responses regardless of type.	false
Retry Delay (ms)	The delay in milliseconds between retries.	0
Timeout	The maximum time that a client will await a response to its request	2000
URL	Input the path only (/v1/images/generations), The base URL is already included (https://api.openai.com). For example, to connect to https://api.openai.com/v1/images/generations, only /v1/images/generations is entered in this field.	/v1/images/generations
Use Exponential Backoff	Specifies whether to use a pre-defined exponential backoff strategy for retries.	false

---

Summarize Text

Summarize a given text | key: summarizeText

Input	Notes	Example
Connection
Model / Deployment Name	Specifies either the model deployment name (when using Azure OpenAI) or model name (when using non-Azure OpenAI) to use for this request.	gpt-3.5-turbo
Text to Summarize		Two independent experiments reported their results this morning at CERN, Europe's high-energy physics laboratory near Geneva in Switzerland. Both show convincing evidence of a new boson particle weighing around 125 gigaelectronvolts, which so far fits predictions of the Higgs previously made by theoretical physicists. As a layman I would say: 'I think we have it'. Would you agree? Rolf-Dieter Heuer, CERN's director-general, asked the packed auditorium. The physicists assembled there burst into applause.

{
  "data": [
    {
      "text": "How are you today?",
      "index": 0,
      "logprobs": null,
      "finishReason": null
    }
  ]
}

---