Detect entities over pre-deployed model
POST {{baseUrl}}/actions/detectLanguageEntities?modelVersion=V2.1&isPii=false
The API extracts entities in text records. For each entity, its type and confidence score (between 0 and 1) is returned.
Limitations: - A text may be up to 1000 characters long.
Request Params
Key | Datatype | Required | Description |
---|---|---|---|
modelVersion | string | Named Entity Recognition model versions. By default user will get output from V2.1 implementation. | |
isPii | boolean | If this parameter is set to true, you only get PII (Personally identifiable information) entities | |
like PhoneNumber, Email, Person, and so on. Default value is false. | |||
Request Body
{"text"=>"OCI recently added new services to existing compliance program including SOC, HIPAA, and ISO to enable our customers to solve their use cases. We also released new white papers and guidance documents related to Object Storage, the Australian Prudential Regulation Authority (APRA), and the Central Bank of Brazil. These resources help regulated customers better understand how OCI supports their regional and industry-specific compliance requirements. Not only are we expanding our number of compliance offerings and regulatory alignments, we continue to add regions and services at a faster clip."}
HEADERS
Key | Datatype | Required | Description |
---|---|---|---|
opc-request-id | string | The client request ID for tracing. | |
Content-Type | string | ||
Accept | string |
RESPONSES
status: OK
{"entities":[{"isPii":false,"length":10853719,"offset":-23384121,"score":0.680431104936281,"text":"est sunt id do nulla","type":"deserunt ex irure incididunt"},{"isPii":false,"length":3053400,"offset":28323744,"score":0.48377832204280113,"text":"elit exercitation do","type":"nulla Lorem amet"}]}