⛏️Extraction

Description of extraction for Iris. What is extraction and how can it be used ?

When to use extraction ?

This brick extracts a list of values from a document or a string.

The extracted information can be dates, values, types of information. It will return the citation corresponding to each value in the document in a json

Example of use case

To assist project managers and specialists in analyzing client briefs, eTag highlights, classifies, and centralizes requirements by type: "structural work," "certification," and "high-voltage electrical." In order to extract all requirements from these 300-page documents, eTag is integrated with the Iris Engine and utilizes the extraction API. The API returns the quotations associated with each type of requirement.

You can see : eTag

API

Extraction from a list of strings for the values needed

In the string list, each information to extract will be searched for an extracted.

import requests
import json

token = 'JWT ' + ''  # set your token here
url = "https://iris.egis-group.com/api/cgpt_structure/task_execute/?label_task=extraction_from_string"

payload = json.dumps({
  "values_list": [
    {
      "label": "extract_1",
      "val": "information à extraire du texte"
    },
    {
      "label": "extract_2",
      "val": "information à extraire du texte"
    }
  ],
  "string_list": [
    "Texte duquel extraire les informations"
  ]
})
headers = {
  'Authorization': token,
  'Content-Type': 'application/json'
}

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