NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Rosette Text Analytics connects to a Nagent workspace with an API key. Once it is connected, agents can call 3 Rosette Text Analytics actions: "Address Similarity", "Identify Language" and "Compare Name Similarity". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Rosette Text Analytics, with input parameters and output schema.
ROSETTE_TEXT_ANALYTICS_ADDRESS_SIMILARITYCompares two addresses and returns a similarity score. Addresses can be provided as single strings or as structured objects. The tool is optimized for English, Simplified Chinese, and Traditional Chinese addresses.
Input parameters
The first address to compare. Can be a string or a structured object.
The second address to compare. Can be a string or a structured object.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ROSETTE_TEXT_ANALYTICS_LANGUAGE_IDENTIFICATIONThis tool identifies the natural language of a given text. It takes a string of text as input and returns the detected language along with a confidence score. Optional parameters include specifying a genre (e.g., "social-media"), providing a list of language codes to constrain the identification, and indicating whether to include user-defined languages.
Input parameters
The text to be analyzed.
A URI pointing to the content to be analyzed. Mutually exclusive with content.
If set to true, the endpoint detects regions in multilingual documents and returns a list of language regions in addition to whole-document results. Default is false.
If set to true, enables classification for North Korean (qkp) and South Korean (qkr) dialects. Default is false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ROSETTE_TEXT_ANALYTICS_NAME_SIMILARITYThe 'Name Similarity' tool compares two entity names (Person, Location, or Organization) and returns a similarity score between 0 and 1 to indicate if the names are similar. It is useful for tasks such as record linkage, identity resolution, and data deduplication.
Input parameters
The first name object to be compared.
The second name object to be compared.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 3 Rosette Text Analytics actions on Nagent: "Address Similarity", "Identify Language" and "Compare Name Similarity". Address Similarity: Compares two addresses and returns a similarity score. Each action is listed on this page with its input parameters and its output.
Rosette Text Analytics connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Address Similarity takes 2 required inputs: address1 and address2. It returns data, error and successful.