added

Text Tagging API: New AI module for Talent & Workforce Data Classification

We are happy to announce our latest AI module for Talent & Workforce Data Classification: Tagging API.

HrFlow.ai Text Tagging API python request

HrFlow.ai Text Tagging API python request

😍 Why it’s a big deal for HrFlow.ai users?

Our users can now automatically categorize and classify HR data (texts, documents, sections, paragraphs) according to a library of Taxonomies.

The Tagging API’s first release includes 4 AI algorithms, called taggers, associated to 4 different taxonomies (dictionaries of predictions):

Untitled
Tagger Name / Algorithm KeyTagger Prediction / Labels Taxonomy
tagger-rome-familypredicts the job family (Grand Domaine) associated to the french national taxonomy.
tagger-rome-subfamilypredicts the job subfamily (Domaine) associated to the french national taxonomy.
tagger-rome-categorypredicts the job category (Fiches Métiers) associated to the french national taxonomy.
tagger-rome-jobtitlepredicts the job title (Intitulé de poste) associated to the french national taxonomy.
tagger-hrflow-skillspredicts hard and soft skills associated to HrFlow.ai skills graph

The JSON output of the API provides the list of the most likely predictions with associated names, IDs, and probabilities.


🔧 How does it work?

You can follow our Text Tagging API Guide to start classifying Talent & Workforce Data.

You can also use python to make your first Tagging API request:

import requests
import json

url = "https://api.hrflow.ai/v1/text/tagging"

payload = json.dumps({
  "algorithm_key": "tagger-rome-family",
  "text": "Our client, specialized in the sale and mechanics of heavy goods vehicles with a national network, is looking for heavy goods vehicle mechanics for its sites based in Arras, Lens and Douai.",
  "texts": [],
  "top_n": 3,
  "output_lang": "en",
  "labels":[]
})
headers = {
  'X-USER-EMAIL': 'FILL THIS',
  'X-API-KEY': 'FILL THIS',
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

💡 Useful Links