LogoLogo
AboutBlogLaunch app ↗
v0.20.x
v0.20.x
  • Introduction to AI Testing
  • Welcome to Distributional
  • Motivation
  • What is AI Testing?
  • Stages in the AI Software Development Lifecycle
    • Components of AI Testing
  • Distributional Testing
  • Getting Access to Distributional
  • Learning about Distributional
    • The Distributional Framework
    • Defining Tests in Distributional
      • Automated Production test creation & execution
      • Knowledge-based test creation
      • Comprehensive testing with Distributional
    • Reviewing Test Sessions and Runs in Distributional
      • Reviewing and recalibrating automated Production tests
      • Insights surfaced elsewhere on Distributional
      • Notifications
    • Data in Distributional
      • The flow of data
      • Components and the DAG for root cause analysis
      • Uploading data to Distributional
      • Living in your VPC
  • Using Distributional
    • Getting Started
    • Access
      • Organization and Namespaces
      • Users and Permissions
      • Tokens
    • Data
      • Data Objects
      • Run-Level Data
      • Data Storage Integrations
      • Data Access Controls
    • Testing
      • Creating Tests
        • Test Page
        • Test Drawer Through Shortcuts
        • Test Templates
        • SDK
      • Defining Assertions
      • Production Testing
        • Auto-Test Generation
        • Recalibration
        • Notable Results
        • Dynamic Baseline
      • Testing Strategies
        • Test That a Given Distribution Has Certain Properties
        • Test That Distributions Have the Same Statistics
        • Test That Columns Are Similarly Distributed
        • Test That Specific Results Have Matching Behavior
        • Test That Distributions Are Not the Same
      • Executing Tests
        • Manually Running Tests Via UI
        • Executing Tests Via SDK
      • Reviewing Tests
      • Using Filters
        • Filters in the Compare Page
        • Filters in Tests
    • Python SDK
      • Quick Start
      • Functions
        • login
        • Project
          • create_project
          • copy_project
          • export_project_as_json
          • get_project
          • get_or_create_project
          • import_project_from_json
        • Run Config
          • create_run_config
          • get_latest_run_config
          • get_run_config
          • get_run_config_from_latest_run
        • Run Results
          • get_column_results
          • get_scalar_results
          • get_results
          • report_column_results
          • report_scalar_results
          • report_results
        • Run
          • close_run
          • create_run
          • get_run
          • report_run_with_results
        • Baseline
          • create_run_query
          • get_run_query
          • set_run_as_baseline
          • set_run_query_as_baseline
        • Test Session
          • create_test_session
      • Objects
        • Project
        • RunConfig
        • Run
        • RunQuery
        • TestSession
        • TestRecalibrationSession
        • TestGenerationSession
        • ResultData
      • Experimental Functions
        • create_test
        • get_tests
        • get_test_sessions
        • wait_for_test_session
        • get_or_create_tag
        • prepare_incomplete_test_spec_payload
        • create_test_recalibration_session
        • wait_for_test_recalibration_session
        • create_test_generation_session
        • wait_for_test_generation_session
      • Eval Module
        • Quick Start
        • Application Metric Sets
        • How-To / FAQ
        • LLM-as-judge and Embedding Metrics
        • RAG / Question Answer Example
        • Eval Module Functions
          • Index of functions
          • eval
          • eval.metrics
    • Notifications
    • Release Notes
  • Tutorials
    • Instructions
    • Hello World (Sentiment Classifier)
    • Trading Strategy
    • LLM Text Summarization
      • Setting the Scene
      • Prompt Engineering
      • Integration testing for text summarization
      • Practical considerations
Powered by GitBook

© 2025 Distributional, Inc. All Rights Reserved.

On this page
  • Report an initial run and set that as a baseline
  • Setting baseline in SDK
  • Close a new run in that project
  • Create Test Session

Was this helpful?

Export as PDF
  1. Using Distributional
  2. Testing
  3. Executing Tests

Executing Tests Via SDK

PreviousManually Running Tests Via UINextReviewing Tests

Was this helpful?

Tests can also be executed via the SDK after results data has been reported. This requires the following steps.

Report an initial run and set that as a baseline

Setting baseline in SDK

Close a new run in that project

Create Test Session

Alternatively, you can also set a Run as baseline using the function.

Executing the command for a new run in that same project will finalize the data, enabling it for use in Tests.

Execute the command, providing your new run as the "experiment". Tests will then use the previously-defined baseline for comparisons.

set_run_as_baseline
close_run
create_test_session
From the project details page, click configure tests.
Select the baseline run in the dropdown against which you would like new experiment runs to be compared.