●Change8

Migrating to RAGAS v0.4.0

Version v0.4.0 introduces 2 breaking changes. This guide details how to update your code.

Released: 12/3/2025

2
Breaking Changes
4
Migration Steps
16
Affected Symbols

⚠️ Check Your Code

If you use any of these symbols, you need to read this guide:

ContextRelevanceResponse GroundednessAnswerAccuracyFaithfulnessAnswerCorrectnessSummaryScoreContextRelevanceAnswerRelevancyContextEntityRecallFactualCorrectnessNoiseSensitivityBasePromptInstructorLLMEvaluationDatasetGoogleEmbeddingslangchain modules

Breaking Changes

●Issue #1

The migration of several metrics (ContextRelevance, Response Groundedness, AnswerAccuracy, Faithfulness, AnswerCorrectness, SummaryScore, ContextRelevance, AnswerRelevancy, ContextEntityRecall, FactualCorrectness, NoiseSensitivity) to the modular BasePrompt architecture might require updates to custom metric implementations if they relied on internal structures that have changed.

●Issue #2

LangChain import statements have been updated; users relying on specific internal LangChain imports within RAGAS integrations may need to adjust their code.

Migration Steps

  1. 1
    Review and update any custom metric implementations due to the migration of numerous metrics to the modular BasePrompt architecture.
  2. 2
    Review and update any code relying on specific internal LangChain import paths that were modified.
  3. 3
    Update customizations how-to guides to use collections API and LLM factory as documented.
  4. 4
    Consult the migration guide for v0.4 for detailed instructions on upgrading.

Release Summary

This release introduces major architectural updates, migrating numerous metrics to a modular BasePrompt system and enhancing LLM provider support via instructor.from_provider and dual adapter capabilities. It also includes several bug fixes related to LangChain integration and LLM detection.

Need More Details?

View the full release notes and all changes for RAGAS v0.4.0.

View Full Changelog