POST
/
models
/
v2
/
dslim
/
bert-base-NER
token-classification
curl --request POST \
  --url https://api.bytez.com/models/v2/dslim/bert-base-NER \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "text": "John Doe is a software engineer at Google"
}'
{
  "error": "<string>",
  "output": [
    {
      "entity": "B-PER",
      "score": 0.9996556043624878,
      "index": 1,
      "word": "John",
      "start": 0,
      "end": 4
    },
    {
      "entity": "I-PER",
      "score": 0.999683141708374,
      "index": 2,
      "word": "Do",
      "start": 5,
      "end": 7
    },
    {
      "entity": "I-PER",
      "score": 0.9945255517959595,
      "index": 3,
      "word": "##e",
      "start": 7,
      "end": 8
    },
    {
      "entity": "B-ORG",
      "score": 0.9984006285667419,
      "index": 9,
      "word": "Google",
      "start": 35,
      "end": 41
    }
  ]
}

Authorizations

​
Authorization
string
header
required

Set Authorization header to BYTEZ_KEY 'Authorization: YOUR_BYTEZ_KEY_HERE'

Body

application/json

Schema for token-classification models

​
text
string
required

The input text

Example:

"John Doe is a software engineer at Google"

Response

Successful token-classification response.

​
error
string | null
required

Null on success; otherwise an error message.

​
output
any[]
required

Successful response with classified tokens

Example:
[
  {
    "entity": "B-PER",
    "score": 0.9996556043624878,
    "index": 1,
    "word": "John",
    "start": 0,
    "end": 4
  },
  {
    "entity": "I-PER",
    "score": 0.999683141708374,
    "index": 2,
    "word": "Do",
    "start": 5,
    "end": 7
  },
  {
    "entity": "I-PER",
    "score": 0.9945255517959595,
    "index": 3,
    "word": "##e",
    "start": 7,
    "end": 8
  },
  {
    "entity": "B-ORG",
    "score": 0.9984006285667419,
    "index": 9,
    "word": "Google",
    "start": 35,
    "end": 41
  }
]