Data requests

Elevate conversations with dynamic, real-time content from external resources for personalized, powerful interactions using NLX's data requests

What's a Data request?

Data requests are custom integrations that allow you to send and retrieve data from tools in your tech stack. Their most common use is to provide dynamic values in a conversation that are fetched from external resources (e.g., databases, APIs, etc.).

With the use of a Data request node in a flow, you can trigger an API call during conversation, 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

  • Send an email and confirm its success

To access, click Resources in your workspace menu and choose Data requests:

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

A Data request's Settings tab provides a few options:

  • Description: Enter or modify an explanation of the resource for better filing and organization in the workspace, or for providing context to an LLM when assigning the Data request as a tool in agentic mode

  • Tags: Add or remove Resource tags for better filing and organization in the workspace

  • 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 a 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 variables 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

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

Last updated