api-inference documentation

Token Classification

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Token Classification

Token classification is a task in which a label is assigned to some tokens in a text. Some popular token classification subtasks are Named Entity Recognition (NER) and Part-of-Speech (PoS) tagging.

For more details about the token-classification task, check out its dedicated page! You will find examples and related materials.

Recommended models

This is only a subset of the supported models. Find the model that suits you best here.

Using the API

Python
JavaScript
cURL
import requests

API_URL = "https://api-inference.huggingface.co/models/dslim/bert-base-NER"
headers = {"Authorization": "Bearer hf_***"}

def query(payload):
	response = requests.post(API_URL, headers=headers, json=payload)
	return response.json()
	
output = query({
	"inputs": "My name is Sarah Jessica Parker but you can call me Jessica",
})

To use the Python client, see huggingface_hub’s package reference.

API specification

Request

Payload
inputs* string The input text data
parameters object Additional inference parameters for Token Classification
        ignore_labels string[] A list of labels to ignore
        stride integer The number of overlapping tokens between chunks when splitting the input text.
        aggregation_strategy string One of the following:
                 (#1) ’none’ Do not aggregate tokens
                 (#2) ’simple’ Group consecutive tokens with the same label in a single entity.
                 (#3) ’first’ Similar to “simple”, also preserves word integrity (use the label predicted for the first token in a word).
                 (#4) ’average’ Similar to “simple”, also preserves word integrity (uses the label with the highest score, averaged across the word’s tokens).
                 (#5) ’max’ Similar to “simple”, also preserves word integrity (uses the label with the highest score across the word’s tokens).

Some options can be configured by passing headers to the Inference API. Here are the available headers:

Headers
authorization string Authentication header in the form 'Bearer: hf_****' when hf_**** is a personal user access token with Inference API permission. You can generate one from your settings page.
x-use-cache boolean, default to true There is a cache layer on the inference API to speed up requests we have already seen. Most models can use those results as they are deterministic (meaning the outputs will be the same anyway). However, if you use a nondeterministic model, you can set this parameter to prevent the caching mechanism from being used, resulting in a real new query. Read more about caching here.
x-wait-for-model boolean, default to false If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error, as it will limit hanging in your application to known places. Read more about model availability here.

For more information about Inference API headers, check out the parameters guide.

Response

Output type depends on the stream input parameter. If stream is false (default), the response will be a JSON object with the following fields:

Body
(array) object[] Output is an array of objects.
        entity_group string The predicted label for that group of tokens
        score number The associated score / probability
        word string The corresponding text
        start integer The character position in the input where this group begins.
        end integer The character position in the input where this group ends.

If stream is true, generated tokens are returned as a stream, using Server-Sent Events (SSE). For more information about streaming, check out this guide.

< > Update on GitHub