Natural Language Processing

Semantex NLP operations' request on provided content

NER

Named Entity Recognition (NER) is an NLP task used to identify important named entities in the text such as people, places, organizations, date, or any other category. (Recommend for short text content)

Securityapi_key
Request
query Parameters
lang
required
string

The two letter language code

Example: lang=en
text
required
string

The text content with UTF-8 text representation

Example: text=Mark Zuckerberg is one of the founders of Facebook, a company from the United States
Responses
200

200 response

400

Missing required request parameters

403

The request is forbidden (Please input a valid API key)

get/text/nlp/ner
Request samples 
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
NER
Named Entity Recognition (NER) is an NLP task used to identify important named entities in the text such as people, places, organizations, date, or any other category. (Recommend for long text content)


Securityapi_key 
Request 
Request Body schema: application/json
required
text
required
string  non-empty 
The text content with UTF-8 text representation


 
lang
required
string
The two letter language code


 Enum: "en" "fr" "es"  
Responses 
200
200 response


400
Invalid request body


403
The request is forbidden (Please input a valid API key)


post/text/nlp/ner
Request samples 
application/json
{
  • "text": "Mark Zuckerberg is one of the founders of Facebook, a company from the United States",
  • "lang": "en"
}
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
PII-NER
Personally Identifiable Information (PII) Entity Recognition (ER) is an NLP task used to identify important named entities in the text such as people, places, organizations, date, or any other category.


Securityapi_key 
Request 
Request Body schema: application/json
required
text
required
string  non-empty 
The text content with UTF-8 text representation


 
ishtml
boolean
 Default:  false
A boolean flag that should be set to true if text is in HTML markup.


 
random
number  [ 0 .. 1 ] 
 Default:  0
Controls the amount of randomness in the generated text. Lowering this will result in the output to be more deterministic.


 
model
string
 Default:  "gpt4-o"
The generative model to use.


 Enum: "gpt4-o" "gpt4-o-mini" "gpt4" "gpt4-t" "o1" "o1-mini"  
Responses 
200
200 response


post/text/nlp/pii/llm
Request samples 
application/json
{
  • "text": "Hello Zhang Wei, your social insurance number 888-456-2345 will be sent to you at 4 Bond Street, Toronto ON M5J 3A2. tomorrow by noon. Could you confirm that you were indeed 18 years old."
}
Response samples 
application/json
{ }
POS
Part-of-speech (POS) tagging is a popular Natural Language Processing process which categorizes words in a text (corpus) in correspondence with a particular part of speech, depending on the definition of the word and its context. (Recommend for short text content)


Securityapi_key 
Request 
query Parameters
lang
required
string
The two letter language code


 
 Example:  lang=en
text
required
string
The text content with UTF-8 text representation


 
 Example:  text=Mark Zuckerberg is one of the founders of Facebook, a company from the United States
Responses 
200
200 response


400
Missing required request parameters


403
The request is forbidden (Please input a valid API key)


get/text/nlp/pos
Request samples 
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
POS
Part-of-speech (POS) tagging is a popular Natural Language Processing process which categorizes words in a text (corpus) in correspondence with a particular part of speech, depending on the definition of the word and its context. (Recommend for long text content)


Securityapi_key 
Request 
Request Body schema: application/json
required
text
required
string  non-empty 
The text content with UTF-8 text representation


 
lang
required
string
The two letter language code


 Enum: "en" "fr" "es"  
Responses 
200
200 response


400
Invalid request body


403
The request is forbidden (Please input a valid API key)


post/text/nlp/pos
Request samples 
application/json
{
  • "text": "Mark Zuckerberg is one of the founders of Facebook, a company from the United States",
  • "lang": "en"
}
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
NER parse
Named Entity Recognition using LLM models.


Securityapi_key 
Request 
Request Body schema: application/json
required
text
required
string  non-empty 
The text content with UTF-8 text representation


 
ishtml
boolean
 Default:  false
A boolean flag that should be set to true if text is in HTML markup.


 
random
number  [ 0 .. 1 ] 
 Default:  0
Controls the amount of randomness in the generated text. Lowering this will result in the output to be more deterministic.


 
model
string
 Default:  "gpt4-o"
The generative model to use.


 Enum: "gpt4-o" "gpt4-o-mini" "gpt4" "gpt4-t" "o1" "o1-mini"  
Responses 
200
200 response


post/text/nlp/ner/llm
Request samples 
application/json
{
  • "text": "Mark Zuckerberg is one of the founders of Facebook, a company from the United States"
}
Response samples 
application/json
{ }
Lang Detect
Detect the language of the given text content. (Recommend for short text content)


Securityapi_key 
Request 
query Parameters
algo
string
The algorithm used to detect the source language


 
text
required
string
The text content with UTF-8 text representation


 
 Example:  text=Google Translate ist ein mehrsprachiger neuronaler maschineller Übersetzungsdienst, der von Google entwickelt wurde, um Texte, Dokumente und Websites von einer Sprache in eine andere zu übersetzen. Es bietet eine Website-Schnittstelle, eine mobile App für Android und iOS und eine API, die Entwicklern hilft, Browsererweiterungen und Softwareanwendungen zu erstellen.
Responses 
200
200 response


400
Missing required request parameters


403
The request is forbidden (Please input a valid API key)


get/text/nlp/langdetect
Request samples 
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
Lang Detect
Detect the language of the given text content. (Recommend for long text content)


Securityapi_key 
Request 
Request Body schema: application/json
required
text
required
string  non-empty 
The text content with UTF-8 text representation


 
object
Parameter content for language detection


 
Responses 
200
200 response


400
400 response


403
The request is forbidden (Please input a valid API key)


post/text/nlp/langdetect
Request samples 
application/json
{
  • "text": "Mark Zuckerberg is one of the founders of Facebook, a company from the United States"
}
Response samples 
application/json
{
  • "status": {
    },
  • "result": {
    }
}
➔ Next to Enrichments/Classification