Skip to content

OpenAI

OpenAI nodes let you use GPT models, embeddings, and image generation in your workflows. Each operation is a separate node.

All nodes require an OpenAI connection configured with your API key.

Nodes

Chat Completion

Generate text using GPT models.

FieldDescriptionNotes
ModelModel to use (e.g., gpt-4o, gpt-4o-mini)Required
System PromptSystem message to set behaviorOptional. Supports templates
User MessageUser message / promptRequired. Supports templates
TemperatureRandomness (0.0 - 2.0)Default: 1.0
Max TokensMaximum tokens in the responseOptional

Returns an object with the generated text in the content field.

Embedding

Create vector embeddings from text.

FieldDescriptionNotes
ModelEmbedding model (e.g., text-embedding-3-small)Required
InputText to embedRequired. Supports templates

Returns an object with the embedding vector in the embedding field.

Image Generation

Generate images using DALL-E.

FieldDescriptionNotes
ModelImage model (e.g., dall-e-3)Required
PromptImage descriptionRequired. Supports templates
SizeImage dimensions (1024x1024, 1792x1024, 1024x1792)Default: 1024x1024
Qualitystandard or hdDefault: standard

Returns an object with the image URL in the url field.

Common Patterns

AI-Powered Data Enrichment

  1. DataStore Query — fetch records
  2. OpenAI Chat — generate descriptions, summaries, or classifications per record
  3. DataStore Update — write enriched data back

Categorize Incoming Data

  1. Webhook — receive data
  2. OpenAI Chat — classify the input using a system prompt
  3. Switch — route based on the AI's classification