Use image inputs
Overview
The Prompt Playground supports image inputs for working with multi-modal models, like GPT-4o. This feature allows you to iterate on tasks such as image caption generation, visual QA, and more.
You can pass images into your prompts by uploading image URLs as variables. These are used as inputs in your LLM calls—perfect for experimenting with visual content alongside text.
Step-by-Step: Adding Image Inputs
1. Open the Prompt Playground
Navigate to Prompt Playground from the sidebar. Select a multi-modal model (e.g., gpt-4o
) from the dropdown.
2. Add an Image Input Variable
Click the image icon (🖼️) in the variables section to define an image input.
Give your image variable a descriptive name (e.g.,
white_lotus_hotel
)Click "Add Variable"

3. Upload an Image URL
Paste a supported image URL into the input field (JPG, PNG, or base64 formats are accepted).
Example:
https://example.com/images/hotel.jpg
Click "Submit" once the image is loaded.

4. View Results Side-by-Side
Run your prompt. The playground will display:
The image input
The LLM-generated output
Example Output:
“Unwind in style: Where luxury meets tranquility by waterside elegance.”
#LuxuryGetaway #PoolsideParadise

Creating Image Datasets and Using Them in the Playground
Method 1 - CSV Upload:
Prepare images → Upload to accessible URLs
Create CSV → Include image URLs and variables
Upload to Arize → Use "Create via CSV" in Datasets
Map columns → Set image URL column as image variable
Use in Playground → Reference images with
{{variable_name}}
Method 2 - From Traces:
Existing traces → Must contain image URLs in input/output/attributes
Create dataset → Use trace-to-dataset functionality
Auto-mapping → Image URLs extracted as variables
Use in Playground → Same as CSV method
Supported Image Formats
JPG/JPEG ✅
PNG ✅
GIF ✅
SVG ✅
WebP ✅
URL Types Supported
Web URLs:
https://example.com/image.jpg
Cloud Storage:
gs://bucket/image.png
,s3://bucket/image.jpg
Data URLs:
data:image/png;base64,iVBORw0K...
Last updated
Was this helpful?