Documentation updates

Updated run tests notebooks

validmind-library

2.12.4

documentation

Learn the basics of how to use the ValidMind Library to run tests with our updated introductory notebooks for running dataset-based tests and comparison tests.

"What is ValidMind?" product tour

documentation

26.03

documentation

highlight

We added a new interactive product tour covering the key capabilities of the ValidMind platform: inventory management, workflows, reporting, documentation and testing, ongoing monitoring, and regulatory alignment.

Standardized support references

documentation

26.03

documentation

enhancement

We standardized all support references across the documentation to use support.validmind.com and support@validmind.com.

Custom URL support for training pages

documentation

26.03

documentation

enhancement

Training pages now support custom ValidMind URLs. Click the Settings icon to configure your organization's URL for interactive exercises.

AWS Marketplace integration documentation

documentation

26.03

documentation

enhancement

You can now find documentation for signing up to ValidMind via AWS Marketplace, enabling you to streamline billing through your existing AWS account.

Reorganized ValidMind Library developer guides

documentation

26.03

documentation

highlight

We restructured the ValidMind Library developer guides to help you find information more easily. The new "How-To" section groups guides for running tests and using library features, while code samples are now organized by use case category.

Expanded AI governance training

documentation

26.03

documentation

highlight

We expanded the AI governance training course with richer content across all four modules: understanding AI governance, managing AI use cases, configuring AI workflows, and compliance and oversight. New media assets demonstrate platform capabilities.

New notebook for documenting agentic AI systems

validmind-library

2.11.3

documentation

enhancement

A new notebook shows you how to build and document an agentic AI system with the ValidMind Library. You construct a LangGraph-based banking agent that selects and invokes tools in response to user requests, assign AI evaluation scores to your agent, run accuracy, RAGAS, and safety tests, and log the results to the ValidMind Platform.

Add troubleshooting for SSL issues

documentation

26.01

documentation

Troubleshooting guidance is now available to help you address SSL verification errors when initializing the ValidMind Library.

AI governance overview, use case guides, and governance training

documentation

26.01

documentation

highlight

We have expanded our AI governance documentation with an overview of the platform's compliance capabilities, use case guides for major regulatory frameworks (EU AI Act, SR 11-7, SS1/23, E-23), and training materials to help teams implement compliant workflows.

Simplified platform login

documentation

25.12

documentation

We have simplified the process of logging into the ValidMind platform from our documentation site. The login button now takes you directly to the correct location, eliminating the need to choose from multiple options.

System access requirements

documentation

25.12

documentation

We have introduced a new documentation page outlining the system access requirements for using the ValidMind platform. The page provides information on the URLs to allow through your firewall and the supported browsers.

Updated community resources

documentation

25.11

documentation

Our community engagement is evolving, and we're excited to share new ways for you to connect with us. While our Slack community channels will be retired on November 15, 2025, there are many other spaces where you can stay involved:

Add support for the DeepEval dataset in LLM tests

validmind-library

2.9.5

documentation

enhancement

highlight

This update enhances the integration between DeepEval and the ValidMind library by adding support for a new dataset type specific to large language models (LLMs). You can now use various LLM tests from the DeepEval library. We have introduced new row-level metrics that return arrays.

Removed legacy notebooks

validmind-library

2.9.5

documentation

enhancement

This update removes multiple legacy agent demo notebooks and associated code samples that were previously used to demonstrate the integration of LangChain, LangGraph, and banking-specific agent functionality with the ValidMind Library.

New ValidMind public REST API reference

documentation

25.09

documentation

highlight

To enable you to programmatically interact with models, groups, business units, use cases, and templates, we have introduced an API reference in our documentation: ValidMind Public REST API Reference

Fix `codeblock` formatting and import modular CSS

documentation

25.09

bug

We have fixed an issue with codeblock formatting that previously caused incorrect text positioning when specifying a language, such as Python. Codeblocks now display correctly with proper formatting and text alignment.

Enable PII detection in tests with new notebook

validmind-library

2.9.3

documentation

enhancement

deprecation

Learn how to enable and configure Personally Identifiable Information (PII) detection when running tests with the ValidMind Library using the new enable_pii_detection.ipynb notebook. This update replaces the deprecated configure_pii_detection.ipynb notebook. You can choose to include PII in test descriptions or in the test results logged to the ValidMind platform.

Revamped Administrator Fundamentals course with new modules

documentation

25.08

documentation

highlight

We have completely revamped the Administrator Fundamentals course with four new modules to enhance your skills: Developer Fundamentals

Create rebrandable docs site with Kubernetes manifest configuration

documentation

25.08

enhancement

The ValidMind documentation site Docker image now supports full customization for white-label deployments and branded environments.

Enhance administrator quickstart documentation for ValidMind setup

documentation

25.08

documentation

enhancement

We've introduced a new quickstart experience for organization administrators, providing a user-friendly guide to managing your organization on the ValidMind platform. This update covers the essentials of setting up ValidMind, including adding foundational units and defining detailed access permissions for your users before inviting them to the platform.

Enhance `predict_fn` in `init_model` to support multiple output columns

validmind-library

2.8.29

documentation

This update enhances the predict_fn callable function parameter in init_model to support multiple output columns. You can now return either a single value or a dictionary from the function. If a dictionary is returned, the key named prediction will be used as the prediction column. Additional keys in the dictionary can be included as extra columns in the dataset object.

Update links in training FAQ

documentation

25.07

bug

This update updates the documentation links in the site/training/program/training-faq.qmd file.

Revamp quickstart for model development with ValidMind

documentation

25.07

documentation

enhancement

We have revamped the quickstart experience for model developers to provide a user-friendly introduction to using ValidMind for documenting models. This update covers the basics of using ValidMind to develop models. It guides you through registering your first model, using the ValidMind Library to run tests and document a model, and then reviewing your generated model documentation on the ValidMind platform.

New quickstart for model validation

documentation

25.07

documentation

enhancement

We've introduced a new quickstart experience for model validation, providing an easy introduction to ValidMind. This update guides you through using the ValidMind Library to test and evaluate a champion model. You'll learn to add your test results as evidence in your validation report on the ValidMind platform.

Updated workflow documentation and configuration

documentation

25.07

documentation

highlight

We have enhanced our user guides with a revamped section on model workflows. This update offers clear instructions on configuring workflows to suit your organizational needs, whether for model development, validation, implementation, ongoing monitoring, auditing, or other risk management activities. Once configured, you can seamlessly transition your models through the different stages of their lifecycle.

Create rebrandable documentation site with Kubernetes configuration

documentation

25.07

enhancement

The ValidMind documentation site Docker image now supports full customization for white-label deployments and branded environments.

Add section to inject custom context via docstring

validmind-library

2.8.26

documentation

enhancement

This update enhances the Jupyter notebook add_context_to_llm_descriptions.ipynb by introducing a new section. This section guides you on embedding explicit instructions within a test's docstring to influence LLM-generated test result descriptions. Titled Add test-specific context using the docstring, it addresses the issue where non-instructional context in docstrings was previously ignored by the LLM. You are now advised to format specific lines as instructions using syntax like: INSTRUCTION…

Interfaces to support code explainer feature in ValidMind

validmind-library

2.8.26

documentation

enhancement

highlight

This update introduces an experimental feature for text generation tasks within the ValidMind project. It includes interfaces to utilize the code_explainer LLM feature, currently in the experimental namespace to gather feedback.

Revamped Developer Fundamentals training into four modules

documentation

25.06

documentation

highlight

We have revamped our Developer Fundamentals course into four modules, each with clear learning outcomes to enhance your training experience:

Updated content block features in documentation

documentation

25.06

documentation

We have reorganized and expanded our documentation on templates within the ValidMind platform. This supports the release of our updated content block interface and text block library.

Updated Validator Fundamentals courses

documentation

25.06

documentation

highlight

We have revamped our Validator Fundamentals course into four modules, each with clear learning outcomes:

Manage model stakeholder types in documentation

documentation

25.05

documentation

We have introduced several enhancements to the documentation for managing roles and stakeholder types within the ValidMind platform. These updates aim to provide clearer guidance and improve your ability to manage model inventory fields effectively.

User guide updates for attestation management

documentation

25.05

documentation

highlight

Model attestation is now available. This feature enables you, as a model owner or validator, to formally review and certify key details about a model at a specific point in time. It supports internal governance and compliance with external requirements. You can track the attestation process through clear status updates and role-specific tasks.

Add introductory validation notebooks

documentation

25.05

documentation

This update enhances the ValidMind documentation and testing framework with several improvements:

Add missing export ongoing monitoring document section to docs

documentation

25.05

documentation

This update introduces a new feature that lets you export ongoing monitoring documentation for models. It includes the previously missing steps necessary for this process.

Add RAG benchmarking demo notebook

validmind-library

2.8.20

documentation

enhancement

We have introduced a comprehensive notebook, rag_benchmarking_demo.ipynb, to help you benchmark Retrieval-Augmented Generation (RAG) models using the ValidMind library. This notebook allows you to compare multiple configurations for the RAG RFP use case.

New notebook series for model validation with ValidMind

validmind-library

2.8.20

documentation

highlight

Explore our new series of introductory notebooks designed for model validation with ValidMind. These notebooks guide you through the entire process, tailored to common scenarios:

Add text support for custom test descriptions

validmind-library

2.8.20

documentation

enhancement

highlight

We have enhanced the custom test framework, allowing you to define custom descriptions for your tests. If a test returns a string, it will be used as the test description, overriding the automatic description generation.

Embed Validating Models 101 playlist in Guides section

documentation

25.04

documentation

We have introduced a series of short videos to guide you through validating models on our platform:

Embed video on adding tests in developer docs

documentation

25.04

documentation

We have added a short FAQ-style video to the developer documentation. This video guides you on how to find tests provided by ValidMind and integrate them into your own model documentation:

Add developer fundamentals videos and training fixes

documentation

25.04

documentation

Discover our 10 short videos designed to guide you through the model documentation process as a developer. Learn how to generate model documentation with tests, add your own tests, edit content online, and submit your documentation for validator review:

Enhance mathematical formula support in content blocks

documentation

25.04

documentation

We've improved the documentation by refining the formatting and instructions for contributing and working with mathematical formulas. You can now use the new LaTeX formula editor for a more streamlined experience.

Enhance export options for model documentation and validation reports

documentation

25.04

documentation

This update enhances the export functionality for model documentation and validation reports by introducing additional options and information.

Update training content and website styling

documentation

25.04

documentation

We’ve added a training overview, learning paths, and a sample training plan to guide you on your training journey. An FAQ section is now available, connecting common questions to relevant learning paths.

Add breaking changes and deprecation page under releases to support new processes

documentation

25.04

documentation

We have introduced an interactive historical record of breaking changes and deprecations to the ValidMind AI risk platform. This update helps you stay informed about important changes to our product.

Fix broken notebook link

documentation

25.04

bug

documentation

This update addresses a bug in the release notes for January 31, 2025.

Restructure developer portal for ValidMind model development series

documentation

25.04

documentation

This update refactors the navigation and documentation structure of the project.

Add URL configuration to Docker images

documentation

25.04

other

You can now configure the Docker image for the ValidMind documentation site to meet your specific needs. This update simplifies deployment in your infrastructure by allowing you to set two parameters:

New Jupyter notebook for validating an application scorecard model

validmind-library

2.8.17

documentation

enhancement

Discover how to independently assess an application scorecard model with our new Jupyter notebook, Validate an application scorecard model. You can use ValidMind to evaluate a model's development through comprehensive testing and analysis, including benchmarking with challenger models.

Expose log text interface for qualitative text sections

validmind-library

2.8.17

documentation

enhancement

highlight

You can now log free-form text content in the ValidMind Library to enhance your model documentation. This update introduces the log_text function, allowing you to easily integrate text data into your documentation.