Semantic String Comparison
This model compares two strings for similarity in context, intent and meaning and provides the result as percentage score of the similarity. This model can be used to search and find matches of content based on the similarity as defined above instead of strict keyword based matching.
For example, finding the mention of price for a product can be based on the comparison string value of "cost of the product", whereas the cost of the product can be specified as "max retail price". By using this model, all such references to the value of the product can be identified regardless of the presence of a matching keyword.
Parameter Name | Parameter Type | Required |
---|---|---|
input | Text | Yes |
comparison string | Text | Yes |
Rest API Input Example
Parameter Name | Parameter Type | Example |
---|---|---|
| | |
| | |
| | |
Rest API Output Example
Every model execution output consists of the following standard output parameters
- input
- The input string required for the model to extract the categories
- original input
- This is the input provided to the first step in model which is retained across multiple steps in a Data Machine workflow.
- final result
- The result of the model executed in the final step of the Data Machine workflow
- sessionid
- A unique session id that is generated for every execution of a Data Machine which can be used to retain results across multiple sessions
- status
- The result of the Data Machine execution. If all of the steps in a sequence are successfully executed, a value of "Completed" is provided. If the execution is interrupted at any point, a value of "Terminated" is provided with the reason for Termination.