Image Recognition

Image Recognition

Image Recognition services inspect image URLs and return generated text.

Setup

1. Open the Groq integration page.
2. Choose Add Image Recognition.
3. Enter a friendly service name.
4. Select a vision-capable model.
5. Optionally set a system prompt to guide answers.

Service Call

action: groq.analyze_image
data:
  prompt: Describe anything unusual in this camera image.
  image_url: https://example.com/snapshot.jpg
  model: meta-llama/llama-4-scout-17b-16e-instruct
response_variable: groq_image

Built-In Fallback Models

The setup flow prefers live Groq model discovery. If discovery is unavailable, the integration has built-in fallback model IDs:

• meta-llama/llama-4-scout-17b-16e-instruct
• meta-llama/llama-4-maverick-17b-128e-instruct

OCR Notes

OCR support is present in the service architecture and service schema, but the setup flow currently exposes Image Recognition as the user-facing vision service.

If you need text extraction, use an Image Recognition prompt that asks the model to transcribe visible text, or use groq.extract_text_from_image if it is available in your installed version.