OpenAI integration

What it does

The OpenAI integration lets your agency invoke GPT chat completions, create embedding vectors, and inspect the model catalog from inside any workflow. Connect a client's OpenAI key once and your workflows can summarize incoming form submissions, classify support tickets, rewrite copy, generate structured JSON for downstream actions, or build a semantic index over a client's knowledge base, all without leaving TaskJuice.

Connect an OpenAI account

1. Open your workspace in TaskJuice and navigate to Connections.
2. Choose OpenAI and click Connect.
3. In a new tab, open the OpenAI API keys page signed in as the client (or as your agency, if the client has delegated key creation to you).
4. Click Create new secret key, give it a name that identifies the workspace, and copy the sk-... value.
5. Paste the key into TaskJuice and save the connection.

To rotate or revoke the key later, return to the OpenAI API keys page and delete the entry; create a new key and update the TaskJuice connection.

Triggers

OpenAI does not publish a public webhook surface, so the integration is action-only. Use a Schedule or another app's trigger to invoke OpenAI actions inside a workflow.

Actions

• openai/create-chat-completion generates a chat completion against a chosen model (for example, gpt-4o-mini or gpt-4o) with a list of messages and optional temperature, max tokens, top-p, and response-format controls.
• openai/create-embedding returns an embedding vector for an input string using a chosen embedding model such as text-embedding-3-small or text-embedding-3-large, with optional dimensionality override.
• openai/list-models returns the model catalog available to the authenticated key, useful for surfacing a model picker to end users or for branching on model availability.

Known limitations

• The integration calls the OpenAI REST API with the connected key. Per-key rate limits, monthly spend caps, and model-access entitlements are governed by the client's OpenAI organization, not by TaskJuice. When OpenAI returns a 429, TaskJuice surfaces it as a retryable rate-limit error and honors the recommended backoff.
• Streaming responses are not exposed. Each chat completion runs as a single request and resolves only after the full response is returned by OpenAI.
• Embedding requests accept a single input string per call. For batch embedding, fan out across a Loop node so each item runs as its own request.
• The integration is action-only. To react to events in real time, use a Schedule trigger, a polling trigger from another app, or an inbound webhook from a different source and call OpenAI inside the workflow.