Zuva DocAI

Reference

Embed Contracts AI into your product workflows using Zuva DocAI. No need for AI development from the ground up, leverage the DocAI APIs to extract information from your contracts.

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	Zuva Support
URL	https://zuva.ai/support/
Email	support@zuva.ai

Connector Metadata
Publisher	Zuva Inc.
Website	https://zuva.ai/
Privacy policy	https://zuva.ai/privacy/
Categories	AI

This Connector enables users to find and extract entities, sentences, and paragraphs from contracts (and related documents), leveraging Zuva's best-in-class Contracts AI. Designed and trained to pinpoint legal clauses across multiple industries and use cases, this connector provides a plug-and-play suite of modules to embed Contracts AI in your workflows. This Connector comes with OCR to read your documents, as well as document classification and normalization capabilities.

Prerequisites

You will need a Zuva account and a DocAI token. Get started by signing up for a free account.

How to get credentials

Zuva DocAI has multiple regional servers. You will need to create an API token for the specific region that you wish to use.

Create and/or sign into your account at zuva.ai.
Navigate to the DocAI console
Select the region you would like to use.
Copy the base URL for the region to your connection.
Create a token and copy it to use in your connection.

See the DocAI quickstart guide for more information about Zuva accounts and tokens.

Get started with your connector

To use the Zuva DocAI connector, you will need to set a flow similar to the following:

Step 1: Obtain a file

For testing purposes, you can create an "Instant cloud flow" in Power Automate. Choose "Manually trigger a flow" and create the flow. Add an input, and choose the "File" type.

Step 2: Submit a file

Add the Submit a file action, and choose the "File Content" from the previous step as the input.

Note: the file should not be transformed in any way (i.e, no base64 encoding). DocAI only accepts raw binary data.

Step 3: Start processing the file

Choose which service you'd like to use by adding one of the following actions:

Create Language Classification Request
Create Document Classification Request
Create Multi-Level Classification Request
Create Field Extraction Request
Create OCR Request

Each of these accepts the file ID (returned from the Submit a file action) as input.

The field extraction additionally requires field IDs as inputs. Field IDs can be found in the Field Library (sign-in required), from AI trainer if you have trained custom fields, or programmatically using the Get Field List action.

Step 4: Poll for completion of the request

Use a Do Until block (found in the "Control" section), and add the correct status check action to the inside of the block:

Get Field Extraction Request Status
Get Language Classification Request Status
Get Document Classification Request Status
Get MLC request Status
Get OCR Request Status

The Get ____ status action takes as input the request ID from its corresponding Create ____ Request action.

You should also add a 10 second Delay block inside the Do until block, to ensure that the file has sufficient time to process.

Set the condition for the Do Until block to Is Finished? is equal to true.

Step 4: Get results

Finally, use one of the Get results Action corresponding to your request, using the Request ID from the original Create operation as input:

Get Field Extraction Request Text Results
Get Language Classification Request Status
Get Document Classification Request Status
Get MLC request Status
Get OCR Results Text
Get OCR Results Images

Note that for Language, Document Classification and MLC, the results are included in the Status response.

You may wish to check the DocAI documentation for more information about the structure of field extraction results.

Known issues and limitations

Fields per request

A maximum of 100 fields may be included in a single Create Field Extraction Request action.

Custom fields

The connector does not support any of DocAI's endpoints related to training custom fields or getting an individual field's metadata.

Differences with underlying API

Additionally, please note that connector functionality does not correspond one-to-one with the documentation for the underlying API. In particular, the connector:

Exposes an extra is_finished boolean, which can be used to tell if the request is either complete or failed
All requests operate on single files, rather than batches of multiple files.

Common errors and remedies

Be sure to upload raw binary, rather than base64-encoded strings. You can use the OCR service and check that it returns the expected text.

FAQ

Where can I find additional information about Zuva DocAI?

https://zuva.ai/docai/

Where can I find additional documentation about Zuva DocAI?

https://zuva.ai/documentation/

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
Token	securestring	Your DocAI token	True
Base URL	string	e.g. https://us.app.zuva.ai/api/v2	True

Throttling Limits

Name	Calls	Renewal Period
API calls per connection	100	60 seconds

Actions

Create an OCR Request	Create a new request for OCR to be applied to the specified file.
Create Document Classification Request	Create a request for classification of the specified document.
Create Field Extraction Request	Create a new request for extractions from the specified file.
Create Language Classification Request	Create a request for the language of the specified file.
Create Multi-Level Classification Request	Create a request for multi-level classification of the specified file.
Delete a File	Delete an existing file from Zuva.
Get Document Classification Request Status	Get status and available results for an existing document classification request.
Get Field Extraction Request Results	Get text results from a completed field extraction request.
Get Field Extraction Request Status	Check the status of an existing field extraction request.
Get Field List	Get a list of all fields available to you.
Get Language Classification Request Status	Get status and available results for an existing document classification request.
Get MLC request Status	Get status and available results for an existing MLC request.
Get OCR Request Images	Get the images from a completed OCR request.
Get OCR Request Status	Check the status of an existing OCR request.
Get OCR Request Text	Get the text from a completed OCR request.
Normalize dates	Normalize a string containing one or more dates. For each date found, the endpoint returns a set of integers representing the year, month and day.
Submit a file	Submit a file to Zuva DocAI.

Create an OCR Request

Operation ID:: CreateOcrRequest

Create a new request for OCR to be applied to the specified file.

Parameters

Name	Key	Required	Type	Description
File ID	file_id		string	The unique identifier for the file, as returned by the SubmitFile operation.

Returns

Name	Path	Type	Description
OCR Request ID	request_id	string	ID used to obtain status and results of the OCR request.

Create Document Classification Request

Operation ID:: CreateDocumentClassificationRequest

Create a request for classification of the specified document.

Parameters

Name	Key	Required	Type	Description
File ID	file_id		string	The unique identifier for the file, as returned by the SubmitFile operation.

Returns

Name	Path	Type	Description
Classification Request ID	request_id	string	ID to use to obtain status and results of this request.

Create Field Extraction Request

Operation ID:: CreateFieldExtractionRequest

Create a new request for extractions from the specified file.

Parameters

Name	Key	Required	Type	Description
File ID	file_id		string	The file to extract text from.
Field IDs	field_ids		array of string	The IDs of the fields to extract.

Returns

Name	Path	Type	Description
Extraction Request ID	request_id	string	ID to use to obtain status and results of this request.

Create Language Classification Request

Operation ID:: CreateLanguageClassificationRequest

Create a request for the language of the specified file.

Parameters

Name	Key	Required	Type	Description
File ID	file_id		string	The unique identifier for the file, as returned by the SubmitFile operation.

Returns

Name	Path	Type	Description
Language Request ID	request_id	string	ID to use to obtain status and results of this request.

Create Multi-Level Classification Request

Operation ID:: CreateMlcRequest

Create a request for multi-level classification of the specified file.

Parameters

Name	Key	Required	Type	Description
File ID	file_id		string	The unique identifier for the file, as returned by the SubmitFile operation.

Returns

Name	Path	Type	Description
MLC Request ID	request_id	string	ID to use to obtain status and results of this request.

Delete a File

Operation ID:: DeleteFile

Delete an existing file from Zuva.

Parameters

Name	Key	Required	Type	Description
File ID	file_id	True	string	ID of the file to delete.

Returns

response: string

Get Document Classification Request Status

Operation ID:: GetDocumentClassificationRequestStatus

Get status and available results for an existing document classification request.

Parameters

Name	Key	Required	Type	Description
Request ID	request_id	True	string	Request ID of the document classification request, as returned by CreateDocumentClasssificationRequest.

Returns

Name	Path	Type	Description
Classification Request Status	status	string	Status of the request (one of 'queued', 'processing', 'complete' or 'failed').
Is Finished?	is_finished	boolean	Boolean indicating whether the request has reached a terminal state (complete or failed).
Classification	classification	string	The type of document that was detected.
Is Contract?	is_contract	boolean	Whether the document was recognized as a contract or not.

Get Field Extraction Request Results

Operation ID:: GetFieldExtractionRequestResults

Get text results from a completed field extraction request.

Parameters

Name	Key	Required	Type	Description
Extraction Request Id	request_id	True	string	Unique identifer of an existing extraction request, as returned by CreateExtractionRequest.

Returns

Name	Path	Type	Description
Results	results	array of object	An array of the results of the field extraction.
Field ID	results.field_id	string	The unique identifier for the extracted field.
Extractions	results.extractions	array of object	An array of results extracted for this particular field.
Text	results.extractions.text	string	The text that was extracted for the field.
Spans	results.extractions.spans	array of object	Information about the location of the text within the document.
Start	results.extractions.spans.start	integer	The index of the first character of the extraction within the document text.
End	results.extractions.spans.end	integer	The index of the last character of the extraction within the document text.
Start	results.extractions.spans.pages.start	integer	The page number on which the extraction starts.
End	results.extractions.spans.pages.end	integer	The page number on which the extraction ends.

Get Field Extraction Request Status

Operation ID:: GetFieldExtractionRequestStatus

Check the status of an existing field extraction request.

Parameters

Name	Key	Required	Type	Description
Extraction Request Id	request_id	True	string	Unique identifer of an existing extraction request, as returned by CreateExtractionRequest.

Returns

Name	Path	Type	Description
Field Extraction Request Status	status	string	Status of the request (one of 'queued', 'processing', 'complete' or 'failed').
Is Finished?	is_finished	boolean	Boolean indicating whether the request has reached a terminal state (complete or failed).

Get Field List

Operation ID:: GetFieldList

Get a list of all fields available to you.

Returns

Name	Path	Type	Description
		array of object
Field ID	field_id	string	The unique identifier for the field.
Name	name	string	The name of the field
Description	description	string	A description of the field.
Bias	bias	double	The bias used by the underlying ML model.
F-score	f_score	double	The F-score of the field, a statistical measure of its accuracy.
Precision	precision	double	The precision of the field.
Recall	recall	double	The recall of the field.
Document Count	document_count	integer	The number of documents the field has been trained on.
Is Custom?	is_custom	boolean	Boolean indicating whether the field is custom.
Is trained?	is_trained	boolean	Boolean indicating whether a custom field has been trained.

Get Language Classification Request Status

Operation ID:: GetLanguageClassificationRequestStatus

Get status and available results for an existing document classification request.

Parameters

Name	Key	Required	Type	Description
Request ID	request_id	True	string	Request ID of the language classification request, as returned by CreateLanguageRequest.

Returns

Name	Path	Type	Description
Language Request Status	status	string	Status of the request (one of 'queued', 'processing', 'complete' or 'failed').
Is Finished?	is_finished	boolean	Boolean indicating whether the request has reached a terminal state (complete or failed).
Language	language	string	The primary detected language of the document.

Get MLC request Status

Operation ID:: GetMlcRequestStatus

Get status and available results for an existing MLC request.

Parameters

Name	Key	Required	Type	Description
Request ID	request_id	True	string	Request ID of the MLC request, as returned by CreateMlcRequest.

Returns

Name	Path	Type	Description
MLC Request Status	status	string	Status of the request (one of 'queued', 'processing', 'complete' or 'failed').
Is Finished?	is_finished	boolean	Boolean indicating whether the request has reached a terminal state (complete or failed).
Classifications	classifications	array of string	The hierarchical classifications of the document.

Get OCR Request Images

Operation ID:: GetOcrRequestImages

Get the images from a completed OCR request.

Parameters

Name	Key	Required	Type	Description
OCR Request Id	request_id	True	string	Unique identifer of an existing OCR request, as returned by CreateOcrRequest.

Returns

A zip file containing each page of the document as an image.

Images: binary

Get OCR Request Status

Operation ID:: GetOcrRequestStatus

Check the status of an existing OCR request.

Parameters

Name	Key	Required	Type	Description
OCR Request Id	request_id	True	string	Unique identifer of an existing OCR request, as returned by CreateOcrRequest.

Returns

Name	Path	Type	Description
OCR Request Status	status	string	Status of the request (one of 'queued', 'processing', 'complete' or 'failed').
Is Finished?	is_finished	boolean	Boolean indicating whether the request has reached a terminal state (complete or failed).

Get OCR Request Text

Operation ID:: GetOcrRequestText

Get the text from a completed OCR request.

Parameters

Name	Key	Required	Type	Description
OCR Request Id	request_id	True	string	Unique identifer of an existing OCR request, as returned by CreateOcrRequest.

Returns

Name	Path	Type	Description
Text	text	string	OCR text of the document.

Normalize dates

Operation ID:: NormalizeDates

Normalize a string containing one or more dates. For each date found, the endpoint returns a set of integers representing the year, month and day.

Parameters

Name	Key	Required	Type	Description
Text	text		string	The text string to normalize.

Returns

Name	Path	Type	Description
Request ID	request_id	string	ID of the request
text	text	string	The original text that was provided.
sha-256	sha-256	string	SHA-256 hash of the original text.
date	date	array of object	date
Day	date.day	integer	The day of the month as an integer.
Month	date.month	integer	The month represented as an integer between 1 and 12.
Year	date.year	integer	The year represented as an integer.

Submit a file

Operation ID:: SubmitFile

Submit a file to Zuva DocAI.

Parameters

Name	Key	Required	Type	Description
File	File		binary	Binary file content or plain text string to upload. Binary content should NOT be Base64-encoded.

Returns

Name	Path	Type	Description
File ID	file_id	string	The Zuva-assigned unique identifier for the file.
Content type	attributes.content-type	string	Detected MIME content type of the file
Expiration	expiration	string	The time at which the file is scheduled to be deleted from DocAI.

다음을 통해 공유

Zuva DocAI

Prerequisites

How to get credentials

Get started with your connector

Step 1: Obtain a file

Step 2: Submit a file

Step 3: Start processing the file

Step 4: Poll for completion of the request

Step 4: Get results

Known issues and limitations

Fields per request

Custom fields

Differences with underlying API

Common errors and remedies

FAQ

Where can I find additional information about Zuva DocAI?

Where can I find additional documentation about Zuva DocAI?

Creating a connection

Default

Throttling Limits

Actions

Create an OCR Request

Parameters

Returns

Create Document Classification Request

Parameters

Returns

Create Field Extraction Request

Parameters

Returns

Create Language Classification Request

Parameters

Returns

Create Multi-Level Classification Request

Parameters

Returns

Delete a File

Parameters

Returns

Get Document Classification Request Status

Parameters

Returns

Get Field Extraction Request Results

Parameters

Returns

Get Field Extraction Request Status

Parameters

Returns

Get Field List

Returns

Get Language Classification Request Status

Parameters

Returns

Get MLC request Status

Parameters

Returns

Get OCR Request Images

Parameters

Returns

Get OCR Request Status

Parameters

Returns

Get OCR Request Text

Parameters

Returns

Normalize dates

Parameters

Returns

Submit a file

Parameters

Returns

Definitions

string

binary

추가 리소스