Jobs Asking

In this article, we'll take a look at how HrFlow.ai Job Asking API works by interacting with the endpoint 🧠 Ask a question to a Job indexed in a Board. We will test queries through our public HrFlow.ai Postman collection.

The goal is to streamline and enhance the job posting process by effortlessly extracting essential information from job listings. This powerful tool not only facilitates the populating of every required field for job board postings but also enables the creation of succinct and tailored job descriptions that cater specifically to the desired profiles. With the ability to summarize and extract both explicit and implicit information from job listings, Asking Job empowers users to efficiently and effectively connect with their target audience and optimize the recruitment process.

📘

Prerequisites

1. ✨ Create a Workspace
2. 🔑 Get your API Key
3. 🧠 Activate Asking API
4. 🔌 Create a Board

📘

API Endpoint

Get more information about the endpoint 🧠 Ask a question to a Job indexed in a Board.

Step 1: Index Jobs in your Board

Jobs in HrFlow.ai are indexed in special folders called Boards. You can refer to 🔌 Create a Board to create a Board.

First, you need to adapt your data to the HrFlow.ai Job Object format. All the required fields and values structures are defined at 📖 Job Object. Then, your Job Object is indexed in your desired Board using the indexing endpoint.

You can find a more thorough description of the indexing endpoint at 💾 Index a Job in a Board.

📘

Index Job with a reference

• Specifying a reference eases Job updates in HrFlow.ai
• This reference is optional and uniquely identifies a Job in HrFlow.ai.
• Job always has a unique identification key (Job key) generated by HrFlow.ai.

🚧

Indexed Jobs in HrFlow.ai must be kept up-to-date

To prevent outdated results from our Searching API, ensure updating all Jobs on which changes have taken place. Check here for more details on how to 💾 Edit a Job indexed in a Source.

Step 2: Get your First Asking Results with Postman

Let's dig deeper into our Job Asking endpoint possibilities. In the following, we are going to use our Postman Collection and focus on the endpoint that allows us to 🧠 Ask a question to a Job indexed in a Board.

📘

HrFlow.ai Postman

Check our publication on HrFlow.ai Postman to get started with our Postman collection.

1. Configure your Postman Environment

Once you have followed the first steps described in this article, you will land on this page:

First, click on the "Environments" tab on the left side of your Postman window. Then, fill in the Empty - Environment template with the correct values. The compulsory variables for Jobs Asking are:

• x-api-key: follow the steps from 🔑 API Authentication to retrieve it
• x-user-email: follow the steps from 🔑 API Authentication to retrieve it
• board_key: the Board where the job is indexed
• job_key/job_reference: the key/reference of the Job to whom we wish to ask a question

Finally, save the environment and ensure that you selected Empty - Environment as your current environment.

2. Ask a question to Job in a Board

Now that the environment is selected, we can test our first request to Ask a question to a Job indexed in a Board. To do so, fill in your parameters :

• [MANDATORY] questions: the list of questions you wish to pose to the job. Your list should consist of strings. For example :
  • Single question :["What is the start date for this job? (DD-MM-YYYY)"]
  • Multi questions : ["Summarize the job", "Is there a start date for this position?"]

Let's break down the Asking request's response. The field data of the response object is a list of answers in order they were asked. Consequently, the first answer will correspond to the answer for the first question, the second answer will correspond to the answer for the second question, and so on.

• To effectively formulate and pose questions to the Job Asking, it is crucial to be clear and precise in your inquiries.
• The model has the capability to comprehensively analyze all fields within a Job.
• The model is trained to respond in the active voice, providing direct answers. However, it is possible for the model to give inconsistent or incorrect responses, so it's advisable to validate information when necessary.
• For closed-ended questions, where you expect a binary response (yes/no), you can specify the choices within the question. For example: Is there a start date for this position? (yes/no)
• For some specific closed-ended questions, it might be more suitable to use the Tagging API. For instance : What is the typical work space in the company (fast, moderate, flexible)?
• You can also set a default value if you believe the answer may not necessarily be found within the job. For example : Exact address of the job (default: n/a) . Generally, when the model is unsure and no default value is specified, it may respond with "N/A" or "null."
• If you want the model to provide a response in a specific format, such as a JSON list of entities, you can structure your question accordingly. For example : Among the following options, which best matches the job (returns a JSON list): Full-time, Permanent, Temporary, Part-time, Fixed-term contract, Internship, Apprenticeship, Freelance, Civic service. A valid response can be expressed as a string ["Full-time", "Permanent"]
• Lastly, it's worth noting that the model is multilingual, and it will respond in the same language in which the question was posed.

Some examples of questions and their answer

Advanced Topics

1. Try Asking in your Favorite Programming Language

Once you have tried the request in Postman, you can directly convert it to work with your favorite programming language. Here is an example with Python and the module Requests.

import requests
import json

url = "https://api.hrflow.ai/v1/job/asking"

questions = [
  "What is the start date for this job? (DD-MM-YYYY)",
  "Is language training offered to employees?"
]
payload = {
  "board_key": "FILL_WITH_BOARD_KEY",
  "key": "FILL_WITH_JOB_KEY",
  "questions": json.dumps(questions)
}
headers = {
  'X-USER-EMAIL': 'FILL THIS',
  'X-API-KEY': 'FILL THIS',
  'Content-Type': 'application/json'
}

response = requests.request("GET", url, headers=headers, data=payload)
print(response.json())