azureResponsesRunAdapter
The Azure counterpart of
openaiResponsesRunAdapter. Routes runs to an Azure OpenAI deployment that supports the Responses API.Signature
azureResponsesRunAdapter({
getOpenaiAssistant?: (args?: { select?: { id?: false } }) =>
Promise<Assistant | Pick<Assistant, 'id'>>,
waitUntil?: <T>(p: Promise<T>) => void | Promise<void>,
})
Example
import { AzureOpenAI } from 'openai'
import {
supercompat,
azureOpenaiClientAdapter,
azureResponsesRunAdapter,
azureResponsesStorageAdapter,
} from 'supercompat/openai'
const azureOpenai = new AzureOpenAI({
endpoint: process.env.AZURE_OPENAI_ENDPOINT!,
apiKey: process.env.AZURE_OPENAI_API_KEY,
apiVersion: '2024-10-01-preview',
})
const client = supercompat({
clientAdapter: azureOpenaiClientAdapter({ azureOpenai }),
storageAdapter: azureResponsesStorageAdapter(),
runAdapter: azureResponsesRunAdapter(),
})
const response = await client.responses.create({
model: 'my-gpt-4-1-deployment',
input: 'Hello from Azure.',
})
Use your Azure deployment name as
model.