Package com.tnsai.evaluation.evaluators.geval

Interface LLMJudge

Functional Interface:
This is a functional interface and can therefore be used as the assignment target for a lambda expression or method reference.
@FunctionalInterface public interface LLMJudge
Functional interface for LLM-based judging. Accepts a prompt string and returns the LLM's text response.

This abstraction decouples evaluation from any specific LLM client implementation, allowing users to plug in their own client: 


 LLMJudge judge = prompt -> myLlmClient.chat(prompt);
 var evaluator = new GEvalEvaluator("coherence", "Is the response coherent?", judge);
Since:
0.2.0

  • Method Summary

    Modifier and Type
    Method
    Description
    String
    judge(String prompt)
    Sends a prompt to an LLM and returns the text response.

  • Method Details

    • judge

      String judge(String prompt)
      Sends a prompt to an LLM and returns the text response.
      Parameters:
      prompt - the full prompt to send
      Returns:
      LLM response text