Data requests

Elevate conversations with Data Requests in NLX's Dialog Studio—dynamic, real-time content from external resources for personalized, powerful interactions.

What's a Data request?

Data requests provide dynamic values in a conversation that are retrieved from external resources (e.g., databases, APIs, etc.). Once set up, a data request may be triggered and referenced across any intent flow in the workspace.

With the use of a Data request node, you can prompt information to be pulled in while a conversation is in progress, injecting the results into subsequent nodes in the flow to be relayed in real time:

  • Provide a choice of available appointment times

  • Authenticate a user and later provide information from their profile/account

  • Offer status information

Need more context? See Data request node

Requirements

A data request must always employ the following to function:

Data requests features

ImplementationResponse modelRequest model

Data request settings

Your data request's Settings tab allows you to add or edit optional descriptors and enable a few behaviors:

  • Sensitive: Prevent the values for this data request from appearing in conversation logs. Useful for concealing personally identifiable information (PII). Disabled by default

  • Stream state modifications: Enable if referencing the Data request in an intent flow that has state modifications applied to it and uses a Lifecycle hook to stream the state mods to your data without obstructing processes of the NLU

  • Send context: Provides context attributes available in a conversation session at the time the webhook is called

  • Enable advanced data model: On by default as it supports use of the schema auto-generation feature and additional data structure improvements. Toggling off is not recommended and is only provided for backwards compatibility. This feature will be sunset in 2025.

To delete a data request, select the Delete option under Danger zone. If the data request is used in an intent(s), modify affected flows and create a new bot build/re-deploy to experience the change.

Last updated