OpenAI

What you can do

9 actions, each one call from a workflow or a server function. Triggers come from your app: a row changing, a schedule or a webhook.

• Ask ChatGPTask_chatgpt
  Ask ChatGPT anything you want!
• Generate Imagegenerate_image
  Generate an image using text-to-image models
• Text-to-Speechtext_to_speech
  Generate an audio recording from text
• Transcribe Audiotranscribe
  Transcribe audio to text using whisper-1 model
• Vision Promptvision_prompt
  Ask GPT a question about an image
• Ask Assistantask_assistant
  Ask a GPT assistant anything you want!
• Extract Structured Data from Textextract-structured-data
  Returns structured data from provided unstructured text.
• Translate Audiotranslate
  Translate audio to text using whisper-1 model
• Custom API Callcustom_api_call
  Make a custom API call to a specific endpoint

Set it up

About two minutes, once per project or once for the whole workspace.

1. Open Integrations in the builder

   Backend panel, Integrations tab, then OpenAI. To connect it for every project, use Workspace settings, Integrations.

2. Add your credentials

   An API key (or token) from your OpenAI account, pasted once. It is stored encrypted and only read on the server when an action runs.

   • API key From OpenAI's settings
3. Call an action

   From a workflow, by integration id and action name. The call answers with success, output and, when it fails, the reason.

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

More in AI and ML

• ABAmazon Bedrock
• AOAzure OpenAI
• Claude
• CoCohere
• Deepgram
• DeepSeek
• All of AI and ML