Document AI Konfuzio
Use the document AI Konfuzio Connector to OCR, extract, and retrieve structured information from PDFs, images, handwriting, and scans. Register on https://app.konfuzio.com for free to OCR PDFs and images from various file types, see https://dev.konfuzio.com/web/api.html#supported-file-types. In addition, you can train your custom Document AI following the Tutorial on https://help.konfuzio.com/tutorials/quickstart/ to extract structured information from documents.
This connector is available in the following products and regions:
Service | Class | Regions |
---|---|---|
Logic Apps | Standard | All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD) |
Power Automate | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Power Apps | Premium | All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
Contact | |
---|---|
Name | Helm & Nagel GmbH |
URL | https://help.konfuzio.com |
[email protected] |
Connector Metadata | |
---|---|
Publisher | Helm & Nagel GmbH |
Website | https://konfuzio.com |
Privacy policy | https://konfuzio.com/de/impressum/ |
Categories | Data;Content and Files |
OCR, extract, validate, process and understand the information in documents by connecting to Konfuzio using this connector. Train Konfuzio to understand any file-based carrier of information to automate complex back-office processes and use more data to generate insights. Konfuzio enables business users who use this connector to categorize documents and extract information. Optionally, data scientists can use Konfuzio as an automated text and image labeling tool with a user-friendly web interface to maintain high-quality data sets to build world-class AI, integrate their AI and improve the AI with humans in the loop.
Prerequisites
Register for free on app.konfuzio.com. The free plan provides you with a limited number of features. Have a look at the features of our fee-based service here. If you want to upgrade to a fee-based service please contact us via [email protected].
Set-up a project as described in our quickstart tutorial on help.konfuzio.com.
How to get credentials
Use the username and password which you used to create a user account on app.konfuzio.com as credentials to use the connector.
Get started with your connector
Find the latest step-by-step process for getting started with your connector on help.konfuzio.com.
Known issues and limitations
- The connector supports ca. 70 languages, see dev.konfuzio.com
- The connector supports various file types. Have a look at dev.konfuzio.com for a detailed list of supported file types.
- The connector supports data normalization for strings that refer to numbers, percentages, date values and booleans, see dev.konfuzio.com
Common errors and remedies
Contact us via [email protected] in case of errors.
FAQ
We publish FAQ about the Power Automate Connector on help.konfuzio.com.
Creating a connection
The connector supports the following authentication types:
Default | Parameters for creating connection. | All regions | Not shareable |
Default
Applicable: All regions
Parameters for creating connection.
This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.
Name | Type | Description | Required |
---|---|---|---|
username | securestring | The username for this api | True |
password | securestring | The password for this api | True |
Throttling Limits
Name | Calls | Renewal Period |
---|---|---|
API calls per connection | 100 | 60 seconds |
Actions
Delete a document |
Delete a document. |
Give feedback to the extraction results of a document |
You can give feedback by sending the adapted extraction result dictionary. Example python code:
|
Retrieve the extraction results for a document |
Get all information for a document using its id. The extraction results are available once the processing has finished |
Upload a new document |
Upload a new document |
Delete a document
Delete a document.
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Document ID
|
doc | True | string |
ID of the document you want to delete |
Give feedback to the extraction results of a document
You can give feedback by sending the adapted extraction result dictionary.
Example python code:
import requests
import json
from requests.auth import HTTPBasicAuth
url = f"https://app.konfuzio.com/api/v2/docs/{DOC_ID}/"
auth = HTTPBasicAuth(KONFUZIO_USER, KONFUZIO_PASSWORD)
data = requests.get(url=url, auth=auth).json()
# Mark Extraction as correct.
data['labels']['Bruttozahlweise']['extractions'][0]['correct'] = True
# Add new Extraction which has not been in result list.
data['labels']['Bruttozahlweise']['extractions'].append({'value': '123,45'})
r = requests.patch(url = url, data=json.dumps(data), auth=auth, headers={'Content-Type': 'application/json'},)
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Document ID
|
doc | True | string |
ID of the document you want to patch |
Retrieve the extraction results for a document
Get all information for a document using its id. The extraction results are available once the processing has finished
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
Document ID
|
doc | True | string |
ID of your document in the project |
Upload a new document
Upload a new document
Parameters
Name | Key | Required | Type | Description |
---|---|---|---|---|
File
|
data_file | True | file |
File to send to Host. |
Project ID
|
project | True | integer |
The ID of your project. |
Synchron response
|
sync | boolean |
Default is False |
Returns
Name | Path | Type | Description |
---|---|---|---|
Data file
|
data_file | uri | |
ID
|
id | integer | |
Project
|
project | integer | |
Data file name
|
data_file_name | string | |
Callback URL
|
callback_url | uri | |
Sync
|
sync | boolean | |
Extraction url
|
extraction_url | string |