Document Automation v.34 release
- Updated: 2025/01/06
Review what's new and changed, and the fixes and limitations in Document Automation for the v.34 release.
| What's new | ||||
|---|---|---|---|---|
| New
navigation to access learning instances We have created a new AI section in the navigation menu, which includes Document Automation and other AI-powered products. This streamlined navigation makes it easy to find and access all our AI-enabled offerings. You can access your learning instances using the new navigation: .
|
||||
| New regions
support for generative AI
providers New regions are added for generative AI providers to provide
the following benefits:
The following additional new regions are available for
the generative AI providers:
Document Automation settings | Enable generative AI and other external connections to Document Automation |
||||
| Field-level
validation feedback You now have the option to disable or enable validation feedback for each form and table fields so that users have control over which fields require validation feedback. This option is particularly useful when you need to disable validation feedback for fields that provide desired results without the need for validation feedback or when you need to use alternate solutions such as pre-trained model or generative AI providers to improve data extraction. |
||||
| Support for
new languages in Automation Anywhere user-defined
provider You can now process documents in the following languages when using the user-defined document type and Automation Anywhere (user-defined) provider:
|
| What's changed |
|---|
| Support for longer
regex pattern (Service Cloud Case ID: 01997816) We have extended the regex pattern limit for the Extract field using pattern option to 250 characters, allowing for more detailed and complex patterns. |
| Support for
longer prompts We have extended the prompt limit for the Search query for Generative AI model option to 1000 characters, allowing for more detailed and complex requests. |
| Licensing
enhancements We have implemented enhanced tracking for the following licenses to ensure fair usage. After the license is consumed or expired, extraction will fail with the following error: License expired or not available. Obtain the necessary license.
After a license is consumed or expired, data extraction will fail until the license is renewed. Therefore, before you reach your license limit, review your usage and consider renewing your licenses. |
| Alert for users
when importing existing learning instances An error is displayed when a user tries to import a learning instance that is already imported by another user from IQ Bot to Document Automation using the IQ Bot - Document Automation Bridge package. The error message displays the user ID of the user who previously imported the learning instance. You can request the user to publish the learning instance to the public repository so that other users can access the learning instances. |
| Fixes |
|---|
| You can now process documents using
the Google Vision OCR provider without any
error. Previously, data extraction failed when the Google Vision OCR provider was used without certain licenses. Service Cloud Case ID: 02169589, 02169909, 02166869, 02168877, 02170956, 02171211, 02171455, 02171434, 02170918, 02171534 |
| You can now copy or import learning
instances with validation feedback. Previously, copying or importing of learning instances failed in certain scenarios. |
| You can now use the IQ Bot Pre-processor
package
actions when the Input folder
path contains Japanese characters without seeing
errors. Previously, you were seeing an error in such a scenario. Service Cloud case ID: 02086260 |
| When you update your Control Room to the v.34 release and if the
External Connections option was
enabled, it will be enabled after the update. Previously, this option was disabled in such a scenario. Service Cloud case ID: 02160623 |
| You can now apply multiple
field rules and perform multiple replace actions on the same field simultaneously to
replace characters in the extracted data, without any
issues. Service Cloud case ID: 02124562 |
| You can now process documents
using standard forms successfully when the extraction model is
created using one of the supported languages such as Spanish
(Colombia). Service Cloud case ID: 02138931 |
| If you have integrated the
Standard forms license with Document Automation,
you can now use the Extract data and
Download data
actions to upload or download documents in
.png format without any
issues. Service Cloud case ID: 02119146 |
| You will now be able to use a neural
model in Standard Forms to extract data from PDFs
that contain tables with empty cells. Previously, data extraction from some cells were skipped in such a scenario. Service Cloud Case ID: 02157782 |
| When the Generative AI
driven data extraction option is enabled and you
select a generative AI provider (OpenAI or Anthropic) while
creating a learning instance, you will now be able to select a
different provider later. The option to switch to a different
generative AI provider will be
displayed when editing the learning instance
details. Previously, the option to select a different generative AI provider was not available in such a scenario. |
| When you use the IQ Bot - DA Bridge package and the
Connect Learning Instances from IQ
Bot feature simultaneously and if you delete,
re-import, or reconnect any learning instance, you will no
longer see an incorrect user interface for the learning
instance. Previously, an incorrect user interface was displayed for the learning instance in such a scenario. |
| You can now use the scroll bar
to view all the learning instances while using the
Connect Learning Instances from IQ
Bot feature in Document Automation. Previously, you had to use the mouse scroll option to scroll through the learning instances or use the search option to view a specific learning instance. |
| When you process documents in
migrated learning instances that are using validation rules, the
documents are now processed correctly without the need for
validation when correct values are extracted as per the
validation rules. Previously, in some scenarios, documents were sent for validation though correct values were extracted. |
| Limitations |
|---|
| When you update from a previous
release to v.34 release and if regex patterns were defined in
the regex condition of the Field Rules
and Document Rules, the regex patterns
will be not be visible after the update. However, the regex
patterns will work as they were defined. The same behavior is
seen for learning instances created after the update.
Therefore, we recommend that before you update to v.34 release, ensure that you make note of the regex patterns used in the Field Rules and Document Rules in case you need to modify the regex patterns. |
| When you use the Document Classifier
actions (Classify, Classify documents, and Train
Classifier) and Extract Data action in the Document Extraction
package together in a bot, the bot will fail to execute. Workaround: Ensure that you create separate bots when using any of the actions from the Document Classifier package and the Extract Data action of the Document Extraction package. If you need to execute these bots in a sequence, include these bots in an Automation Co-Pilot process. |
If you have disabled the OCR
provider in the administrator settings and if you are using a
language other than English for your Control Room, you will see an error to enable the OCR provider settings in
English in the following scenarios:
|
| When you add an effect in the
Enhance image action of the IQ Bot Pre-processor
package, the name of the effect type is displayed
as ENHANCEMENT TYPE. Workaround: To view the effect type used, either double-click the name or click the three dots icon to expand and click Edit. |
| Limitations from previous releases |
|---|
| If you copy a learning instance that is using a third-party parser configured in Document Automation and process documents using the copied learning instance, data extraction will fail. |
| When user processes a document on custom process learning instance, the validate document count is not updated post extraction. Also, if user submits the document, the validate document count is updated with the negative value. |
| A user with the Automation Co-Pilot administrator permissions is unable to view the Document Automation tasks that are assigned or requested and are in pending or complete status. |
| If a document contains multiple values similar to the value submitted as the end-of-table indicator during validation (for example, total, subtotal), the system will use the first occurrence of the value as the end-of-table indicator. This value might not always be the value submitted as the end-of-table indicator during validation when you reprocess the document or documents of similar formats. |
| When you set all the table fields
in a learning instance to optional and if any documents
processed using this learning instance are sent for validation,
the validator will not display an option to add a row for the
table fields. Workaround: Set at least one of the table fields to required or delete the empty row from the table to see the Add row button. |
|
When data is extracted using a generative AI provider, a specific field might return an empty value if the response is requested in JSON format within the search query. Workaround: Instead of requesting the field to return the query in JSON format within the search query, request the query result to be in a different format, such as an array or text. |
|
For a public process, you might encounter an error message in
the following scenarios:
Note: No error message is
displayed for the private process. |
| When you are using the IQ Bot Pre-processor
package
actions and if the Output folder
path contains Japanese characters, you will see
an error when processing documents. Workaround: Create an output folder in a folder path that does not contain any Japanese characters and provide the path in the output folder path field. |
IQ Bot
| Limitation |
|---|
| Data extraction performance is slightly impacted after you update to v.34 release. |
Updates to the interface
| Document Automation |
|---|
| A new navigation menu is introduced to access learning
instances:
|
| The Document Automation settings page is revamped
to include separate sections to enable the different generative AI and extraction
providers. New regions are supported for generative AI providers.
|
| A new option to enable field-level validation feedback is
introduced for form and table fields:
|
