Bert-base-NER

NER (Name Entity Recognition) API

The Name Entity Recognition (NER) API endpoint allows you to recognize and extract text entities like location, person, organisation, etc.

Introduction

Named Entity Recognition is a information extraction task. NER is part of Natural Language Processing (NLP) and involves identifying and categorizing key information (named entities) in text into predefined classes, such as person names, organizations, locations, etc.

AI Endpoints makes it easy, with ready-to-use inference APIs. Discover how to use them:

Model concept and configuration

This NER API is based on an Open-Source model: dslim/bert-base-NER. It takes text as input and returns the recognized entities.

Model configuration:

• Input type: Raw text
• Language Support: English
• Output classes: location (LOC), organizations (ORG), person (PER), Miscellaneous (MISC)

How to?

The NER endpoint offers you an optimized way to classify the tokens in your text. Learn how to use them with the following example:

With a simple HTTP client (requests)

First install the requests library:

pip install requests

Next, export your access token to the OVH_AI_ENDPOINTS_ACCESS_TOKEN environment variable:

export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>

If you do not have an access token key yet, follow the instructions in the AI Endpoints – Getting Started.

Finally, run the following Python code:

import os
import requests

url = "https://bert-base-ner.endpoints.kepler.ai.cloud.ovh.net/api/text2ner"
text ='John lived in Amsterdam in 1996, but now he is in Paris'
res_dict = {
    "text": text,
}

headers = {
    "Content-Type": "text/plain",
    "Authorization": f"Bearer {os.getenv('OVH_AI_ENDPOINTS_ACCESS_TOKEN')}",
}

response = requests.post(url, data=text, headers=headers)

if response.status_code == 200:
    # Handle response
    response_data = response.json()
    # Parse JSON response
    latest_end = 0
    for entity in response_data:
        entity["start"] = latest_end+res_dict["text"][latest_end:].index(entity["word"])
        entity["end"] = entity["start"]+len(entity["word"])
        latest_end = entity["end"]
        res_dict["entities"] = response_data
    print(res_dict)
else:
    print("Error:", response.status_code, response.text)

Model rate limit

When using AI Endpoints, the following rate limits apply:

• Anonymous: 2 requests per minute, per IP and per model.
• Authenticated with an API access key: 400 requests per minute, per Public Cloud project and per model.

If you exceed this limit, a 429 error code will be returned.

If you require higher usage, please get in touch with us to discuss increasing your rate limits.

Going Further

For a broader overview of AI Endpoints, explore the full AI Endpoints Documentation.

Reach out to our support team or join the OVHcloud Discord #ai-endpoints channel to share your questions, feedback, and suggestions for improving the service, to the team and the community.