The following sections list every released version of OCP NLU, newest first. Each section comes from the monthly OCP® Release Notes page named in its Released line.
OCP NLU 1.18.0
Released: October 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
New Features
-
Cleanup of unused applications — Preview and delete applications that have not been used for at least 6 months. Business-critical applications are excluded.
-
More languages — Custom NLU supports en-CA, de-AT, de-CH, and Latin American Spanish (es-CO, es-MX, es-AR, es-UY, es-CL, es-PE).
-
Redaction domain — Redaction is available as a domain in Fusion and RB.
-
Upgrade available filter — Filter the application list to those with an upgrade available.
-
Model description — NLU models have a description field.
-
Larger datasets — The dataset upload size limit is increased.
-
More replicas — The replica limit on RB applications is increased.
Improvements
-
Delete during checkout — A deployment can be deleted while a checkout is in progress.
-
Start and stop — Start and stop are disabled when an application has no custom data.
-
Clearer suggestion errors — Suggestion failures no longer include the underlying AI vendor in the error text.
Fixes
-
A background migration no longer overwrites a completed checkout after the upgrade lock is cleared.
-
The evaluation report is saved before the model status changes to EVALUATED.
-
Entity suggestions no longer fail when the response is wrapped in a markdown code block.
OCP NLU 1.17.2
Released: September 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
NLU Engine Security Update - This release includes a security update to the NLU Engine, addressing previously reported vulnerabilities with no impact on existing functionality.
OCP NLU 1.17.1
Released: September 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
Fixes
Autocorrect Engine Security Update - This release includes a security update to the Autocorrect engine, addressing previously reported vulnerabilities with no impact on existing functionality.
OCP NLU 1.17.0
Released: August 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
September 29, 2026 |
September 23, 2026 |
September 23, 2026 |
New Features
-
Multi-Intent Recognition Expands to More Languages - Multi-intent recognition, previously limited to English, now extends to Greek, Spanish, German, and French, letting the system detect multiple customer intents in a single utterance across more languages.
-
Recognition accuracy for Greek is also improved with a new encoder ideal for large Greek datasets.
Improvements
-
Consistent Intent Selection Policy After Snapshot Updates - When you switch a running application to a new model snapshot, its intent selection policy now updates automatically to match the new snapshot. Previously, the application kept an outdated policy until you recreated it; scoring results now reflect the current snapshot's policy immediately.
Fixes
-
Resolved issue on working status of applications in both redis issues and large amount of ml models.
OCP NLU 1.16.0
Released: July 2026, August 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
September 8, 2026 |
September 17, 2026 |
September 8, 2026 |
Improvements
-
Larger File Uploads for Training and Evaluation - Training and evaluation file uploads now support files up to 15 MB, up from the previous 10 MB limit, giving you more room to work with bigger datasets.
-
Clearer Snapshot List Layout - Fixed a display issue where the snapshot list could overlap the Cancel and Create buttons, so both stay visible and clickable.
-
Non-Latin Character Support in Context Rules - Context rule matching patterns now accept non-Latin characters, such as Cyrillic script, directly from the console, matching what was already available through the API.
-
Cleaner Model Import Error Handling - When linking a model to an existing artifact fails because of a domain mismatch, the system no longer leaves behind a stray application, keeping your workspace free of unwanted leftovers.
-
Recover from Stuck App Checkouts - You can now unblock and delete an application that's stuck mid-checkout or mid-deletion because its underlying resources were already removed, so you're not left waiting on an unrecoverable state.
-
Cross-Validation Results Travel With Your Model - Exporting, importing, or creating a snapshot of a model now automatically carries its cross-validation results along with it, so validation metrics move with the model instead of being left behind.
-
OCP Console® Overhaul, Phase Two - The OCP Console® continues its refresh with updated modals, drawers, input fields, and data tables for a more consistent look and feel across every section. The new experience can be turned on or off through a feature flag, so you control when you switch over.
-
Simplified Deployment Notifications - Notifications about inactive NLU deployments scheduled to stop are now grouped into a single message per user instead of one per application, with clearer wording letting you know deployments will stop in 24 hours.
-
Clearer Limit Messages for Models and Apps - When you reach a model or application limit, the message now tells you specifically whether it's your account limit or your group's limit, and who to contact, so you know exactly how to proceed.
-
More Reliable xPack Deployments - xPack deployments now check that required components are ready and configurations are in sync before proceeding, and prevent duplicate deployments of the same version, reducing failed or conflicting updates.
OCP NLU 1.15.0
Released: June 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
July 1, 2026 |
July 15, 2026 |
July 3, 2026 |
New Features
-
K-Fold Cross-Validation for NLU Models - You can now run k-fold cross-validation directly from OCP Conversational Natural Language®, enabling a more statistically robust assessment of model performance before deployment. Initiate a validation run, track its progress in real time, and review a full breakdown of results, including per-intent accuracy summaries, confusion patterns, and downloadable detailed reports, all from within the interface. Only one validation run per group runs at a time, preventing conflicts with active training or evaluation jobs.
-
Model Data Validation - Before training, you can now validate a model's training dataset to check its health and integrity. Results are surfaced directly in the interface, helping you catch data issues early and avoid training a model on a flawed dataset.
-
Belgian French (fr-BE) Language Support - OCP Conversational Natural Language® now supports Belgian French (fr-BE) as a new language option, extending coverage for French-speaking users in Belgium.
Improvements
-
Alphabetically Sorted Language List with Human-Readable Names - The language selection dropdown now lists all available languages in alphabetical order and displays them as readable names (for example, "French (Belgium)" instead of "fr-BE"), making it faster and easier to find the right language when creating or configuring a model.
-
Accurate Training Results for Mixed-Case Entity References - Models whose training data includes entity references written in mixed case now train and annotate correctly. Previously, these references were silently excluded from training, causing the deployed model to miss matching phrases. Retraining existing affected models is recommended to pick up the fix.
-
Deployed Snapshot Indicator - The snapshot list now shows a visual indicator next to the snapshot that is currently deployed, making it immediately clear which version is active without needing to navigate away.
-
Configurable Resource Allocation for xPack Deployments - Administrators can now configure CPU limits, CPU reservations, replica counts, and workflow maximums for xPack applications based on their domain and language, providing finer control over resource allocation and performance during deployment.
-
Uninterrupted Annotations During Service Restarts - Annotation requests no longer return errors during the brief window following a service restart or redeployment. The service now completes its internal configuration before accepting traffic, ensuring a smooth experience.
For more information go to Evaluating a model, Training an NLU model, Managing Snapshots of an NLU Model, Deploying a model, and OCP Conversational Natural Language® User Guide.
Fixes
-
This release includes security updates.
OCP NLU 1.14.1
Released: June 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Improvements
-
Consistent xPack Version Across All Servers After Deployment - After deploying a new OCP deep NLU® xPack, all running servers now automatically refresh to the latest version without requiring a manual restart, ensuring consistent recognition behavior across your deployment from the moment a new xPack goes live.
OCP NLU 1.14.0
Released: May 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
June 2, 2026 |
June 22, 2026 |
June 4, 2026 |
New Features
-
xPack Management in the Admin Area - Administrators can now view, update, and remove xPacks directly from the NLU admin panel, with clear distinction between active and deprecated xPacks and the ability to delete deprecated ones. For more information, go to OCP Conversational Natural Language® User Guide.
Improvements
-
Rename Artifacts - Artifacts can now be renamed after they are created, giving you more flexibility to keep your workspace organised. For more information, go to OCP Conversational Natural Language® User Guide.
-
Flexible Group Configuration Updates - Group configuration settings can now be updated individually. Changing a single setting no longer resets all other fields to their default values, reducing the risk of unintended configuration changes.
-
Reliable Full Evaluation and Model Cleanup - Running a full evaluation no longer fails with a duplicate name error when previous temporary evaluation resources were not cleaned up. Deleting a model or artifact now also removes any leftover temporary evaluation resources automatically. For more information, go to Training an NLU model.
-
Improved App Lifecycle Enforcement - Applications that missed their scheduled stop deadline, including those created before version 1.12.0, are now reliably stopped, keeping resource usage accurate and predictable.
-
Simplified Evaluation File Format - The third column in evaluation upload files is now optional. When omitted, a default value is applied automatically, reducing the preparation effort for running a full evaluation.
-
Clear Errors on Model Import with Duplicate Rules - Importing a model that contains duplicate context rules now returns an explicit error message, so you can identify and correct the issue immediately instead of encountering a silent failure. For more information, go to Exporting / importing an NLU model.
Fixes
-
This release includes security updates.
OCP NLU 1.13.0
Released: April 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
May 4, 2026 |
May 18, 2026 |
May 6, 2026 |
New Features
-
New Locale Support - OCP Conversational Natural Language® now supports seven additional locales: Swedish (
sv-SE), Norwegian (no-NO), Dutch Belgium (nl-BE), Dutch Netherlands (nl-NL), Polish (pl-PL), Hebrew (he-IL), and Danish (da-DK). -
Entity Value Suggestions Enhancement - The entity suggestion feature now includes a mandatory description field and an optional system prompt field, allowing you to guide the AI-generated lexicon more precisely and generate more relevant entity values.
Improvements
-
Group-Level NextGen Control - Administrators can now enable or disable NextGen application creation at the group level through a new flag in the Admin Groups area, providing granular control over NextGen feature rollout.
-
Dictionary Upload for xPack Entities - You can now upload CSV files to add values and alternatives to xPack entities, making it easier to extend pre-built entity definitions without manual entry.
-
Refreshed User Interface - The console interface has been updated with improved colors, typography, icons, spacing, and illustrations for a more modern and consistent user experience.
-
Deployment Status Warning - When viewing an artifact that is already deployed, a warning message now appears to inform you that only one deployment per artifact is allowed.
-
Enhanced Context Rule Formatting - The context rule panel now provides clearer instructions and tooltips for advanced formatting options, making it easier to configure complex context rules.
-
Larger Training Dataset Support - The 1MB file size limit for DistilBERT models has been removed, allowing you to upload larger training datasets (up to 3MB) for English models.
-
Improved Error Messaging - When the NLU Engine is temporarily unavailable, the system now returns a clear warning message instead of a generic error, improving the troubleshooting experience.
-
Simplified Resource Limits - Resource limitation logic has been refactored to prioritize group-level limits over environment variables, providing more predictable and manageable resource allocation.
-
Business-Critical Application Protection - Applications marked as business-critical are now kept running indefinitely, regardless of idle period, ensuring uninterrupted service for production deployments.
-
Artifact Renaming - You can now rename existing artifacts through a new API endpoint, making it easier to keep your project organization accurate and up to date.
-
ML Model ID in xPack Response - The xPack API response now includes the associated ML Model ID, making it easier to track versions and perform rollbacks when needed.
-
IAM Authentication - The platform now supports AWS MSK IAM authentication, enhancing security and simplifying credential management in cloud environments.
-
Enhanced Accessibility - The user interface now maintains full functionality at 200 percent zoom level, meeting WCAG 2.1 AA accessibility standards for users with visual impairments.
Security
-
This release includes security updates.
For more information, go to OCP Conversational Natural Language® User Guide.
OCP NLU 1.12.0
Released: February 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
March 11, 2026 |
April 21, 2026 |
March 10, 2026 |
Features
-
Enhanced Address Support: Expanded address formatting and recognition for German (
de-DE) and Ukrainian (uk-UA) locales. -
Australian English ASR: Enabled Speech Recognition (ASR) adaptation support specifically for the
en-AUlocale to improve accuracy for Australian accents. -
Flexible Entity Matching: You can now mark specific entities within a matching pattern as optional, allowing for more natural and varied user inputs.
-
Global NLU Endpoints: Introduced global endpoints for Natural Language Understanding (NLU) to simplify cross-region integrations.
-
Advanced Intent Management: New functionality to automatically drop or disable specific intents using the disableIntentDefault tag or specific entity triggers in annotation responses.
-
Keyboard Navigation: Improved accessibility across the UI with enhanced keyboard shortcuts and navigation support.
-
Model Metadata: The Model GET endpoint now includes the group_asr_enabled field for better visibility into speech settings.
Improvements
-
Enhanced the "Duplicate Name" error message (409) to explicitly include the name of the conflicting application.
-
Simplified the application creation process by removing legacy server version selection.
-
Added protections to prevent the accidental deletion of essential resource packs.
-
Enabled the ability to link non-custom models to Next-Gen applications.
-
Improved version comparison logic to fully support snapshot and suffixed versioning formats.
-
Deprecated the outdated minilm-last-layer encoder to streamline performance.
-
Added a new endpoint to easily view all available ASR adaptation locales.
-
Optimized backend communication between the Fusion API and Storage services.
-
Fixes
-
Health checks were incorrectly triggering for stopped applications.
-
Improved the notification system for expiring applications to ensure timely alerts.
-
Fixed an issue where "Not Found" errors were incorrectly displayed when discarding a checkout.
-
Corrected the validation logic to prevent importing models that don't match the existing domain or language.
-
Optimized the Next-Gen annotation process, significantly reducing processing time.
-
Fixed variable formatting in UI pipelines to ensure consistent interface rendering.
For more information, see the OCP Conversational Natural Language® User Guide.
OCP NLU 1.11.0 Release
Released: January 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
February 10, 2026 |
Rolled-forward |
February 25, 2026 |
Features
-
Contextualization on NLU model (creating context rules)
-
NLU Model full evaluation (including rb part)
-
Support
it-ITlocale -
Additional supported fields NLU contexts (level and prompt)
-
New encoder for english models for decontextualization
-
Group configuration management (changing limits and ASR adaptation enablement)
Improvements
-
More informative message when reaching the model's limit
-
Option to delete all deprecated xpacks at once & update message on logs
-
Option unlock a stuck checkout process
-
ONS Audit Events to Console
Fixes
-
Resolved issue with ";" symbol on suggested utterances
-
Delete faulty deprecated xPack list on rollback
-
Fixes on entities of Weaviate db
Security and Vulnerability Updates
-
Resolved vulnerabilities
-
NLU Integration: Integrated with NLU® Engine 9.0.2.
-
ML Server Integration: Integrated with ML Server 3.3.0.
OCP NLU v1.10.0
Released: October 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
November 12, 2025 |
February 2, 2026 |
November 14, 2025 |
Features & Enhancements
-
Improved Autocorrect Selection: The Fusion UI now replaces the existing fields for autocorrect selection with a more intuitive dropdown interface for easier configuration. Integrating an Autocorrect Application
-
Scoped Entity Support: Introducing support for a JSON part of the prompt for a single scoped entity within the Next-Gen NLU, enabling more precise natural language understanding. Gen AI Applications
-
Efficient Model/Deployment Search: You can now enable sorting for models and deployments, significantly improving efficiency when searching and managing resources.
-
Language-Specific Application Filtering: The AUTOC API now supports filtering applications per language, giving you targeted control over your application deployment.
Fixes & Stability
-
API Health Check Consistency: The
HEALTHCHECK_INTERVALin both ML and AUTOC APIs has been updated to 120000 ms for consistent monitoring. -
Status Reporting: Corrected issues with ML and RB status reporting for accurate monitoring.
-
Fusion UI Stability: The Fusion UI now disables snapshot selection while on checkout, preventing potential errors during the process.
Security
-
NLU Integration: Integrated with NLUengine 8.0.6.
-
ML Server Integration: Integrated with ML Server 3.2.9.
OCP NLU v1.9.0
Released: August 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
September 22, 2025 |
Rolled-forward |
September 23, 2025 |
Features
-
Ability to configure the limit of models and apps per group
-
OCP Personal Access Tokens (PAT) integration with FUSION
Fixes
-
502 error due to nginx smaller timeout than AWS load balancer
-
Fix on non working regex pattern while on global alternatives
-
Deleting Model with ASR enabled, deletes only the ML Model
-
Delete Dataset when model is deleted
-
Datasets Retention Policy
-
Allow checkout cancel on ML model failure
-
ML new endpoint
Get User Limits -
Use private IAM url for k8s environments
-
Update IAM policies/permissions for IAM-setup
OCP NLU v1.8.0
Released: July 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
August 19, 2025 |
August 25, 2025 |
August 19, 2025 |
Added
-
Administrative UI for deployment management – Introduced a new administrative interface to streamline deployment management.
-
Option to unblock Checkout & Upgrade process – Added flexibility to manually unblock checkout and upgrade flows when required.
-
Built-in OutOfScope Class for intentSelectionPolicy – Enhanced intent selection policy with a default OutOfScope class.
-
Autocorrect in Fusion – Enabled autocorrect functionality within Fusion for improved text handling.
Fixes & Improvements
-
Optimized workflow for faster security patch deployment.
-
Multi-Architecture support for improved compatibility across environments.
-
Models are now sorted by creation date when using
?limit=0for listing. -
Added UI restriction to prevent merging incompatible intents.
-
Fixed issue with missing umlaut characters (
de-DE) in Fusion UI suggestions. -
Resolved model confidence rounding discrepancies impacting result accuracy.
-
Upgraded APM agent version in NLU APIs for improved monitoring.
-
Start and Stop actions are now simultaneously available when in working status.
-
Added UI customization support for OEM deployments.
-
Enabled IDM across all production environments.
-
Fixed issue with applications stuck in working status.
-
Introduced dataset integration in Fusion for broader data handling.
-
Added a new Secrets Pipeline step to improve secret management.
-
Increased timeout to 4s in RB API to prevent 504 errors during reference deadlocks.
Security & Vulnerability Updates
-
Addressed NLU Operator vulnerabilities.
-
Integrated with ML Server v3.2.7 for enhanced security.
-
Upgraded to Golang v1.24 for improved stability and patching
-
Migrated artifacts to Nexus Artifactory.
-
Integrated with Autocorrect Server v3.0.2.
-
Integrated with NLUEngine v8.0.5 for the latest security updates.
OCP NLU v1.7.0
Released: May 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
June 16, 2025 |
June 23, 2025 |
June 30, 2025 |
Added
-
NLU Lifecycle Management: Introduced support for managing multiple model versions as snapshots, with the ability to upgrade existing deployments.
-
ASR Adaptation on NLU: Enabled via feature flag (available only on us1).
-
Application Deletion Lock: API-only capability to prevent app deletion—designed for use by MiniApps.
Locale Additions
-
English (Australia) – en-AU
-
Portuguese (Brazil) – pt-BR
Fixes & Improvements
-
Integrated with new ml server version (vulnerability fixes)
-
Resolved invalid group name error.
-
Prevented deletion of models currently in use (checked out).
-
Improved app status updates, even when notification errors occur.
-
Fixed occasional deletion of rb/ml apps during Fusion deployment shutdown.
-
Removed restrictions on start/stop options for production apps.
-
Added limit query parameter support to IDM group fetch requests.
OCP NLU v1.6.0
Released: March 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Added
-
Resources improvement (Stop idle apps if not used within 60days)
-
Support universal en-GB with addresses
Fixed
-
Security patches and updates (nluengine 8.0.3)
-
import model with latest nluengine version
For more information, go to NLU Tab.
OCP NLU v1.5.0
Released: February 2025
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Features and improvements
-
Displaying list of models/apps under a specific organization
-
Ukrainian language added as option to create a custom domain model/app.
-
Option to display list of deprecated RB Xpacks APP Ids
-
Deprecated domains: Banking / Covid and Insurance
-
NextGen entities feature (available under flag only for demo)
-
New ml server version 3.2.4
-
New NLU Engine 8.0.2
Fixes
-
Fix vulnerabilities findings
-
Wrong encoder is exported when exporting the migrated EN model (from 3.1.0 to 3.2.2)
For more information, go to NLU Tab.
OCP NLU v1.4.0
Released: December 2024
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Added
-
Migrating an older version application
-
Translated UI
-
Import model with option to upgrade
-
Managing replicas through the UI
Fixes
-
Bugs and vulnerabilities
OCP NLU v1.3.0
Released: ,
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Features
-
Migrating an older version of an application
-
Translated UI
-
Import model with option to upgrade
-
Managing replicas through the UI
Fixes
-
Bugs and vulnerabilities
OCP NLU v1.2.0
Released:
|
US1 |
US2 |
EU1 |
|---|---|---|
|
Rolled-forward |
Rolled-forward |
Rolled-forward |
Added
-
Business Critical Applications - extra resiliency and failover for business critical NLU apps.
-
Migration steps and indicators for models with a newer version available.
-
ML Server 3.2.2 (a new release containing security fixes)
-
NLU Engine 7.0.0 (a new release containing migration from Spark to Spring Boot technology & security fixes)
Fixed
-
Security patches and updates.