Azure OpenAI

Generate text and embeddings using OpenAI models hosted on Microsoft Azure.

AI and MLCredentials form1 actionAll integrations

On this page

Connect
Call it from a workflow
Actions (1)
ask_gpt
Details

Connect

Auth type: Credentials form (custom_auth). Fill in the fields the provider needs (listed below). They are stored encrypted in the vault.

Field	Type	Description
`endpoint`required	text	Your Azure OpenAI resource endpoint URL
`apiKey`required	secret	Your Azure OpenAI API key
`deploymentName`required	text	The name of your model deployment

In the editor: Backend panel, Integrations tab, then Connect. This connects it for the project.
For every project in a workspace: Workspace settings, Integrations.
Owners and admins choose which integrations members may connect in the admin panel (Integrations tab), and can attach their own OAuth app there.

Call it from a workflow

Pass the action name and its input. The call resolves with { success, output, error? }; a missing connection resolves with success false and the reason. See ctx.integrations.invoke and ctx.integrations.call.

Native workflow

// .workflow.js (native ctx)
export async function run(ctx) {
  const res = await ctx.integrations.invoke("azure_openai", "ask_gpt", {
    "deploymentId": "<deployment name>",
    "prompt": "<question>",
    "maxTokens": 1
  });
  if (!res.success) throw new Error(res.error);
  ctx.log.info("Azure OpenAI answered", { output: res.output });
}

defineWorkflow module

// defineWorkflow module (@app/sdk ctx)
import { defineWorkflow } from "@app/sdk";

export default defineWorkflow({
  id: "azure-openai-ask-gpt",
  name: "Azure OpenAI: Ask GPT",
  description: "Calls Azure OpenAI when a row is created.",
  trigger: { type: "entity_event", entity: "tickets", event: "created" },
  async run(ctx, event) {
    const res = await ctx.integrations.call("azure_openai", {
      "action": "ask_gpt",
      "deploymentId": "<deployment name>",
      "prompt": "<question>",
      "maxTokens": 1
    }) as { success: boolean; error?: string };
    if (!res.success) throw new Error(res.error);
  },
});

From an app (connector proxy)

curl -X POST "$APP_ORIGIN/__appbricx/connector-proxy/azure_openai/ask_gpt" \
  -H "Authorization: Bearer $APP_KEY" \
  -H "content-type: application/json" \
  -d '{"props":{"deploymentId":"<deployment name>","prompt":"<question>","maxTokens":1}}'

Actions

ask_gptin catalog

Ask GPT. Ask ChatGPT anything you want!

Input	Type	Description
`deploymentId`required	text	The name of your model deployment.
`prompt`required	long text	Question
`temperature`optional	number	Controls randomness: Lowering results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive.
`maxTokens`required	number	The maximum number of tokens to generate. Requests can use up to 2,048 or 4,096 tokens shared between prompt and completion depending on the model. Don't set the value to maximum and leave some token…
`topP`optional	number	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 …
`frequencyPenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
`presencePenalty`optional	number	Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the mode's likelihood to talk about new topics.
`memoryKey`optional	text	A memory key that will keep the chat history shared across runs and flows. Keep it empty to leave ChatGPT without memory of previous messages.
`roles`optional	JSON	Array of roles to specify more accurate response

Details

Id: azure_openai
Category: AI and ML
Tags: ai, azure, openai, llm, enterprise, microsoft
Package: @activepieces/piece-azure-openai@0.1.4
Tier: Built in