Arize AI Community Icon

Home
Events

Arize AX Releases
Arize AX Support
Arize News
Arize Observe
Discussions
Introductions
Phoenix Support

Powered by Tightknit

Phoenix Support

Phoenix Support

How to Structure and Format Outputs in the Playground

·Jul 11, 2025 03:08 PM

Hi! Is there any place I can find example on how to sturcture the outputs when using the playground? Most specifically, I'm wondering if I can "pretify" the output

4 comments

· Sorted by Oldest

RunLLM
APP
·
Yes, Phoenix Playground supports structured outputs (like JSON) and will pretty-print them for readability. If your prompt or model is configured to return structured JSON, the Playground UI detects and formats it, making it easier to read and inspect. This feature is available for both tool call outputs and general LLM responses, and improvements like syntax highlighting and collapsible subtrees are planned or already released in recent versions (see here, here, and here).To structure outputs, specify an output schema (e.g., JSON mode) in the prompt editor, and ensure your prompt or model returns JSON-formatted responses. The Playground will then render these outputs in a formatted, human-friendly way. For more on setting up structured outputs, see the official docs and prompt concepts. Would you like a step-by-step example?Sources: - Pretty print JSON strings for structured data outputs - Enhancement: Pretty print structured outputs - JSON output formatting with collapse/expand functionality - Prompt concepts: Response Format - official docs
💡 Hint: Mention RunLLM in the thread for followups.
Xander S.
·
Hey José M., not sure what you mean. Can you elaborate?
José M.
·
Maybe I'm missing something on my prompt , but I'm trying to find a way to better show my json on the output section of the plaground
Xander S.
·
Got it. It looks like this model does not support structured output or tool calling? If not, we don't currently have a way to display plain text outputs in a JSON editor.