Processing Text for Entity Masking

The VoiceHarbor API can also process text-only input to mask specified categories of entities.

Quickstart

import json
import time
import nijtaio

TOKEN = '<token>'
API_URL = 'https://api.nijta.com'
headers = {'Content-Type': 'application/json; charset=utf-8', 'TOKEN': TOKEN}
params = {
    'entities': 'Name,Location',
}

response = nijtaio.send_request(
    ['My name is John', 'I live in New York'],
    params,
    nijtaio.session(TOKEN, api_url=API_URL),
    task='text',
    headers=headers,
    api_url=API_URL
)

task_id = json.loads(response.content)['data']['task_id']
print(f'{task_id = }')

print('Waiting for the batch to be processed.')
status = ''

while status != 'finished':
    time.sleep(1)
    status, anonymized_batch = nijtaio.read_response(task_id, api_url=API_URL)
    print(f'{status = }', end='\r')
print()

for masked_text in anonymized_batch:
    print(masked_text)

print('Done.')

Step by step

Follow the steps below to use the API for text processing:

1. Setup and Configuration: Import necessary libraries and set up your API token and URL.

   Python

   import json
   import time
   import nijtaio
   
   TOKEN = '<token>'
   API_URL = 'https://api.nijta.com'
   headers = {'Content-Type': 'application/json; charset=utf-8', 'TOKEN': TOKEN}
   params = {
       'entities': 'Name,Location',
   }
   

2. Send Text for Processing: Pass a list of text strings and the list of categories you wish to mask.

   Python

   response = nijtaio.send_request(
       ['My name is John', 'I live in New York'],
       params,
       nijtaio.session(TOKEN, api_url=API_URL),
       task='text',
       headers=headers,
       api_url=API_URL
   )
   
   task_id = json.loads(response.content)['data']['task_id']
   print(f'{task_id = }')
   

3. Wait for Processing to Complete: Call the API to check the status of the batch processing.

   Python

   print('Waiting for the batch to be processed.')
   status = ''
   
   while status != 'finished':
       time.sleep(1)
       status, anonymized_batch = nijtaio.read_response(task_id, api_url=API_URL)
       print(f'{status = }', end='\r')
   print()
   

📘

Good to know

The result is kept only for 5 seconds on our server.

1. Retrieve and Display Results: Once processing is complete, retrieve and print the anonymized text.

   Python

   for masked_text in anonymized_batch:
       print(masked_text)
   
   print('Done.')
   

Expected Result

The API returns a list of text strings where the specified entities are masked. For example:

['My name is <Name>', 'I live in <Location>']