• About
  • Get Started
  • Guides
  • Developers
    • Get Started
    • Supported Models
    • Documenting Models

    • TESTING
    • Run Tests & Test Suites
    • Test Descriptions
    • Test Sandbox (BETA)

    • CODE SAMPLES
    • All Code Samples · LLM · NLP · Time Series · Etc.
    • Download Code Samples · notebooks.zip
    • Try it on JupyterHub

    • REFERENCE
    • ValidMind Library
  • FAQ
  • Support
  • Training
  • validmind.com
  • Documentation
    • About ValidMind
    • Get Started
    • Guides
    • FAQ
    • Support

    • Developers
    • ValidMind Library

    • ValidMind Academy
    • Training Courses

    • validmind.com
  • Training
    • ValidMind Academy

    • Fundamentals
    • For Administrators
    • For Developers
    • For Validators
  • Log In
    • Public Internet
    • ValidMind Platform · US1
    • ValidMind Platform · CA1

    • Private Link
    • Virtual Private ValidMind (VPV)

    • Which login should I use?
  1. Documenting models

EU AI Act Compliance — Read our original regulation brief on how the EU AI Act aims to balance innovation with safety and accountability, setting standards for responsible AI use

  • ValidMind Library

  • Model Documentation
  • Quickstart for model documentation
  • Introduction for model developers
  • Supported models
  • Documenting models
    • Document models
    • Install and initialize ValidMind Library
    • Work with test results
    • Store model credentials in .env files

  • Model Testing
  • Run tests & test suites
    • Add context to LLM-generated test descriptions
    • Configure dataset features
    • Document multiple results for the same test
    • Explore test suites
    • Explore tests
    • Dataset Column Filters when Running Tests
    • Load dataset predictions
    • Log metrics over time
    • Run individual documentation sections
    • Run documentation tests with custom configurations
    • Run tests with multiple datasets
    • Intro to Unit Metrics
    • Understand and utilize RawData in ValidMind tests
    • Introduction to ValidMind Dataset and Model Objects
    • Run Tests
      • Run dataset based tests
      • Run comparison tests
  • Test descriptions
    • Data Validation
      • ACFandPACFPlot
      • ADF
      • AutoAR
      • AutoMA
      • AutoStationarity
      • BivariateScatterPlots
      • BoxPierce
      • ChiSquaredFeaturesTable
      • ClassImbalance
      • DatasetDescription
      • DatasetSplit
      • DescriptiveStatistics
      • DickeyFullerGLS
      • Duplicates
      • EngleGrangerCoint
      • FeatureTargetCorrelationPlot
      • HighCardinality
      • HighPearsonCorrelation
      • IQROutliersBarPlot
      • IQROutliersTable
      • IsolationForestOutliers
      • JarqueBera
      • KPSS
      • LaggedCorrelationHeatmap
      • LJungBox
      • MissingValues
      • MissingValuesBarPlot
      • MutualInformation
      • PearsonCorrelationMatrix
      • PhillipsPerronArch
      • ProtectedClassesCombination
      • ProtectedClassesDescription
      • ProtectedClassesDisparity
      • ProtectedClassesThresholdOptimizer
      • RollingStatsPlot
      • RunsTest
      • ScatterPlot
      • ScoreBandDefaultRates
      • SeasonalDecompose
      • ShapiroWilk
      • Skewness
      • SpreadPlot
      • TabularCategoricalBarPlots
      • TabularDateTimeHistograms
      • TabularDescriptionTables
      • TabularNumericalHistograms
      • TargetRateBarPlots
      • TimeSeriesDescription
      • TimeSeriesDescriptiveStatistics
      • TimeSeriesFrequency
      • TimeSeriesHistogram
      • TimeSeriesLinePlot
      • TimeSeriesMissingValues
      • TimeSeriesOutliers
      • TooManyZeroValues
      • UniqueRows
      • WOEBinPlots
      • WOEBinTable
      • ZivotAndrewsArch
      • Nlp
        • CommonWords
        • Hashtags
        • LanguageDetection
        • Mentions
        • PolarityAndSubjectivity
        • Punctuations
        • Sentiment
        • StopWords
        • TextDescription
        • Toxicity
    • Model Validation
      • BertScore
      • BleuScore
      • ClusterSizeDistribution
      • ContextualRecall
      • FeaturesAUC
      • MeteorScore
      • ModelMetadata
      • ModelPredictionResiduals
      • RegardScore
      • RegressionResidualsPlot
      • RougeScore
      • TimeSeriesPredictionsPlot
      • TimeSeriesPredictionWithCI
      • TimeSeriesR2SquareBySegments
      • TokenDisparity
      • ToxicityScore
      • Embeddings
        • ClusterDistribution
        • CosineSimilarityComparison
        • CosineSimilarityDistribution
        • CosineSimilarityHeatmap
        • DescriptiveAnalytics
        • EmbeddingsVisualization2D
        • EuclideanDistanceComparison
        • EuclideanDistanceHeatmap
        • PCAComponentsPairwisePlots
        • StabilityAnalysisKeyword
        • StabilityAnalysisRandomNoise
        • StabilityAnalysisSynonyms
        • StabilityAnalysisTranslation
        • TSNEComponentsPairwisePlots
      • Ragas
        • AnswerCorrectness
        • AspectCritic
        • ContextEntityRecall
        • ContextPrecision
        • ContextPrecisionWithoutReference
        • ContextRecall
        • Faithfulness
        • NoiseSensitivity
        • ResponseRelevancy
        • SemanticSimilarity
      • Sklearn
        • AdjustedMutualInformation
        • AdjustedRandIndex
        • CalibrationCurve
        • ClassifierPerformance
        • ClassifierThresholdOptimization
        • ClusterCosineSimilarity
        • ClusterPerformanceMetrics
        • CompletenessScore
        • ConfusionMatrix
        • FeatureImportance
        • FowlkesMallowsScore
        • HomogeneityScore
        • HyperParametersTuning
        • KMeansClustersOptimization
        • MinimumAccuracy
        • MinimumF1Score
        • MinimumROCAUCScore
        • ModelParameters
        • ModelsPerformanceComparison
        • OverfitDiagnosis
        • PermutationFeatureImportance
        • PopulationStabilityIndex
        • PrecisionRecallCurve
        • RegressionErrors
        • RegressionErrorsComparison
        • RegressionPerformance
        • RegressionR2Square
        • RegressionR2SquareComparison
        • RobustnessDiagnosis
        • ROCCurve
        • ScoreProbabilityAlignment
        • SHAPGlobalImportance
        • SilhouettePlot
        • TrainingTestDegradation
        • VMeasure
        • WeakspotsDiagnosis
      • Statsmodels
        • AutoARIMA
        • CumulativePredictionProbabilities
        • DurbinWatsonTest
        • GINITable
        • KolmogorovSmirnov
        • Lilliefors
        • PredictionProbabilitiesHistogram
        • RegressionCoeffs
        • RegressionFeatureSignificance
        • RegressionModelForecastPlot
        • RegressionModelForecastPlotLevels
        • RegressionModelSensitivityPlot
        • RegressionModelSummary
        • RegressionPermutationFeatureImportance
        • ScorecardHistogram
    • Ongoing Monitoring
      • CalibrationCurveDrift
      • ClassDiscriminationDrift
      • ClassificationAccuracyDrift
      • ClassImbalanceDrift
      • ConfusionMatrixDrift
      • CumulativePredictionProbabilitiesDrift
      • FeatureDrift
      • PredictionAcrossEachFeature
      • PredictionCorrelation
      • PredictionProbabilitiesHistogramDrift
      • PredictionQuantilesAcrossFeatures
      • ROCCurveDrift
      • ScoreBandsDrift
      • ScorecardHistogramDrift
      • TargetPredictionDistributionPlot
    • Prompt Validation
      • Bias
      • Clarity
      • Conciseness
      • Delimitation
      • NegativeInstruction
      • Robustness
      • Specificity
  • Test sandbox beta

  • Notebooks
  • Code samples
    • Capital Markets
      • Quickstart for knockout option pricing model documentation
      • Quickstart for Heston option pricing model using QuantLib
    • Credit Risk
      • Document an application scorecard model
      • Document an application scorecard model
      • Document an application scorecard model
      • Document a credit risk model
      • Document an application scorecard model
    • Custom Tests
      • Implement custom tests
      • Integrate external test providers
    • Nlp and Llm
      • Sentiment analysis of financial data using a large language model (LLM)
      • Summarization of financial data using a large language model (LLM)
      • Sentiment analysis of financial data using Hugging Face NLP models
      • Summarization of financial data using Hugging Face NLP models
      • Automate news summarization using LLMs
      • Prompt validation for large language models (LLMs)
      • RAG Model Documentation Demo
    • Ongoing Monitoring
      • Ongoing Monitoring for Application Scorecard
      • Quickstart for ongoing monitoring of models with ValidMind
    • Regression
      • Document a California Housing Price Prediction regression model
    • Time Series
      • Document a time series forecasting model
      • Document a time series forecasting model

  • Reference
  • ValidMind Library

On this page

  • How do I use the ValidMind Library?
  • How do I generate documentation?
  • What’s next
  • Edit this page
  • Report an issue

Documenting models

Published

February 10, 2025

Use the library to generate model documentation, view the results and refine your documentation in the platform, and collaborate with your team to complete documentation and validation initiatives within the same interface.

How do I use the ValidMind Library?

A typical high-level workflow for model developers consists of four major steps:

graph LR
    A[Develop<br>model] --> B[Generate model<br>documentation]
    B --> C[Refine model<br>documentation]
    C --> D[Submit for review]
    C --> B


1. Develop your model1

In your existing developer environment, build one or more candidate models that need to be validated. This step includes all the usual activities you already follow as a model developer.

1 No available model?
You can still run tests and log documentation with ValidMind as long as you’re able to load the model predictions.

2. Generate model documentation

With the ValidMind Library, generate automated model documentation and run validation tests. This step includes making use of the automation and testing functionality provided by the library and uploading the output to the platform. You can iteratively regenerate the documentation as you work though the next step of refining your documentation.

3. Refine model documentation

In the ValidMind Platform, review the generated documentation and test output. Iterate over the documentation and test output to refine your model documentation. Collaborate with other developers and model validators to finalize the model documentation and get it ready for review.

4. Submit for review

In the ValidMind Platform, you submit the model documentation for review which moves the documentation workflow moves to the next phase where a model validator will review it.

Before you can use the ValidMind Library, you need to verify that the current documentation template contains all the necessary tests for the model you are developing:

  • The template might already be sufficient and you only need to run the template within the library to populate documentation.
  • Or, more likely, the template might need additional tests that you can add these tests via the library.

How do I generate documentation?

This process of verifying the suitability of the the current documentation template and adding more tests to the template is an iterative process:

graph LR
    A[Verify template] --> B[Build template]
    B --> D[Add tests and<br>content blocks]
    D --> E[Add external<br>test providers]
    E --> C[Run template]
    C --> B


Build the template

When the documentation template requires more tests to be added, or if the documentation template does not include a specific content or test block you need:

  • For functionality provided by the ValidMind Library — Add the relevant tests or content blocks for the model use case.
  • For tests not provided by the library — Add your own external test provider.

Run the template

When you have registered all the required tests as content blocks in the documentation template, populate the necessary model documentation by adding this call to your model:

run_documentation_tests()
ValidMind may not support all potential use cases or provide a universally applicable documentation template.

Typically, you initiate the process of putting ValidMind into production by constructing a template specific for your own use case and then refine your model documentation.

What’s next

Document models
Generate model documentation starting with your model or model predictions, load your model or predictions into the library, then finally view the results and refine your documentation in the platform to make it ready for approval.
Install and initialize the ValidMind Library
ValidMind generates a unique code snippet for each registered model to connect with your developer environment. You initialize the ValidMind Library with this code snippet, ensuring that your documentation and tests are uploaded to the correct model.
Work with test results
Once generated via the ValidMind Library, view and add the test results to your documentation in the ValidMind Platform.
Store model credentials in .env files
Learn how to store model identifier credentials in a .env file instead of using inline credentials. This topic is relevant for model developers who want to follow best practices for security when running notebooks.
No matching items
Supported models
Document models

© Copyright 2023-2024 ValidMind Inc. All Rights Reserved.

  • Edit this page
  • Report an issue
Cookie Preferences
  • validmind.com

  • Privacy Policy

  • Terms of Use