How to Use Nested JSON as Input in the Playground

To use a nested JSON input in the Phoenix playground, ensure your dataset row is a valid JSON object and upload it as a dataset. The playground will expose each top-level key (e.g., messages, current_report) as a template variable, which you can reference in your prompt using the template language (e.g., {{messages}} for mustache or {messages} for f-string). When running the prompt, Phoenix will substitute these variables with the corresponding values from your JSON input. For example, your dataset row should look like: LBKS{ "current_report": "", "messages": [ { "content": "", "additional_kwargs": {}, "response_metadata": {}, "id": "" } ], "highlighted_report_section": "", "runtime_functions": [ { "ID": "", "description": "" } ], "mode": "", "approved_report_plan": null, "environment_id": "", "field_documentation": "", "sample_data_context": "{}", "cached_processed_documentation": "" }LBKSUpload this as a dataset, then reference variables in your prompt template as needed. For more, see Using Datasets with Prompts and Creating Datasets.Would you like more detail or a code example?Sources: - Using Datasets with Prompts

💡 Hint: Mention RunLLM in the thread for followups.

2 comments