OpenAI Integration

Connect directly to OpenAI's API for advanced use cases beyond what TinyGPT provides: custom model parameters, DALL-E image generation, Whisper transcription, and fine-tuned models.

When to use OpenAI vs TinyGPT

FeatureTinyGPTOpenAI Integration
SetupNo API key neededRequires OpenAI API key
ModelsTinyGPT defaultGPT-4o, GPT-4, GPT-3.5, DALL-E, Whisper
ConfigurationSimplified (System Prompt + Query + Schema)Full API parameters
Best forStandard classification, extraction, writingAdvanced prompting, image generation, audio
CreditsTinyCommand creditsOpenAI API billing (separate)

Setup

  1. Get an API key from platform.openai.com
  2. App AuthorizationsOpenAI → paste your API key

Available actions

ActionWhat it does
Chat CompletionSend a message to GPT-4/3.5 and get a response
Image GenerationGenerate images with DALL-E
Audio TranscriptionTranscribe audio with Whisper
EmbeddingsGenerate text embeddings

Common patterns

Custom AI with full control

Trigger → HTTP Request (GET context data) → OpenAI Chat Completion (custom system prompt + context) →
  Process response → Send Email

Image generation pipeline

Trigger (product description) → OpenAI DALL-E (generate product image) →
  Upload to storage → Update product record
Tip

Use TinyGPT for most AI tasks; it's simpler and uses TinyCommand credits. Use the direct OpenAI integration only when you need specific models, image generation, audio processing, or fine-tuned models.

Error handling

If this node fails during execution:

  1. The execution stops at this node (unless Continue on error is enabled)
  2. The error appears in the Execution History with the full error message
  3. Downstream nodes don't execute

To handle errors gracefully:

  • Enable Continue on error in the node settings
  • Add an If-Else node after to check if the operation succeeded
  • Route failures to a notification (Send Email, Send Slack)

Debugging

  1. Check the Execution History for the failed run
  2. Click the failed node to see its input and error
  3. Verify the input data is correct (check previous node outputs)
  4. Test with sample data using the Test tab