Add JUnit 5 ScorerExtension for AI model evaluation and associated library
#1173
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gsmet
reviewed
Dec 18, 2024
cescoffier
force-pushed
the
testing-scorer
branch
from
fc4b3af to
be27c81
Compare
geoand
reviewed
Dec 18, 2024
.../scorer-core/src/main/java/io/quarkiverse/langchain4j/testing/scorer/EvaluationStrategy.java
Show resolved
Hide resolved
testing/scorer/scorer-core/src/main/java/io/quarkiverse/langchain4j/testing/scorer/Input.java
Outdated
Show resolved
Hide resolved
| @Override | ||
| public boolean evaluate(EvaluationSample<String> sample, String output) { | ||
| String expectedOutput = sample.expectedOutput(); | ||
| String prompt = this.prompt |
There was a problem hiding this comment.
I could see this being an actual template in the future, but no reason to overcomplicate for now
There was a problem hiding this comment.
Yes. This strategy needs a bit of tuning.
...ng/scorer/scorer-junit5/src/main/java/io/quarkiverse/langchain4j/scorer/junit5/AiScorer.java
Show resolved
Hide resolved
...rer/scorer-junit5/src/main/java/io/quarkiverse/langchain4j/scorer/junit5/SampleLocation.java
Show resolved
Hide resolved
...corer-junit5/src/main/java/io/quarkiverse/langchain4j/scorer/junit5/ScorerConfiguration.java
Show resolved
Hide resolved
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
This comment has been minimized.
…library - Implement `ScorerExtension` to inject and manage Scorer instances in tests. - Support field and parameter injection for Scorer using `@ScorerConfiguration`. - Add support for parameter injection of samples via `@SampleLocation` annotation. - Provide built-in evaluation strategies: - `SemanticSimilarityStrategy` (cosine similarity-based evaluation). - `AiJudgeStrategy` (AI-powered evaluation with customizable prompts). - Add tests for ScorerExtension: - Validate field and parameter injection of Scorer. - Test sample injection from YAML files. - Verify evaluation strategies and reporting. - Document ScorerExtension: - Explain concepts: Scorer, Samples, Evaluation Strategies, Reports. - Usage examples for field/parameter injection and evaluation. - Guide for using built-in strategies and creating custom strategies.
cescoffier
force-pushed
the
testing-scorer
branch
from
be27c81 to
7591433
Compare
Status for workflow
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ScorerExtensionto inject and manage Scorer instances in tests.@ScorerConfiguration.@SampleLocationannotation.SemanticSimilarityStrategy(cosine similarity-based evaluation).AiJudgeStrategy(AI-powered evaluation with customizable prompts).