Using the Playground to preview Textual detection
Last updated
Last updated
The Textual Playground page allows you to see how Textual detects values in plain text. You can either have Textual redact the values, or use a large language model (LLM) to replace detected entity values with realistic synthesized values.
To display the Playground page, in the navigation menu, click Playground.
On the Playground page, as you enter text in the left text area, the redacted or synthesized version displays at the right. It also displays the API redaction response.
On a self-hosted instance of Textual, to use the LLM synthesis option, you must set an OpenAI key as the value of the environment variable SOLAR_OPENAI_KEY.
When Enable LLM Synthesis is in the off position then Textual displays redacted values. Redaction replaces the detected values with token values that represent the entity types.
When Enable LLM Synthesis is in the on position, then Textual uses an LLM to generate synthesized values. Synthesized values are realistic replacement values. Note that when LLM synthesis is enabled, newText is always the entity type. This is because the synthesized values and sentence structure might not correspond directly to the original text.
To clear the text, click Clear.
Textual also provides sample text options for some common use cases. To populate the text with a sample, click Try a Sample, then select the type of sample.
