nirbarazida
/
promptfoo
mirror of https://github.com/promptfoo/promptfoo


  
1

	
2

	
3

	
4

	
5

	
6

	
7

	
8

	
9

	
10

	
11

	
12

	
13

	
14

	
15

	
16

	
17

	
18

	
19

	
20

	
21

	
22

	
23

	
24

	
25

	
26

	
27

	
28

	
29

	
30

	
31

	
32

	
33

	
34

	
35

	
36

	
37

	
38

	
39

	
40

	
41

	
42

	
43

	
44

	
45

	
            import type { GradingConfig } from '../../dist/src/types';
import { installJestMatchers } from './matchers';

installJestMatchers();

describe('toMatchSemanticSimilarity', () => {
  it('should pass when strings are semantically similar', async () => {
    await expect('The quick brown fox').toMatchSemanticSimilarity('A fast brown fox');
  });

  it('should fail when strings are not semantically similar', async () => {
    await expect('The quick brown fox').not.toMatchSemanticSimilarity('The weather is nice today');
  });

  it('should pass when strings are semantically similar with custom threshold', async () => {
    await expect('The quick brown fox').toMatchSemanticSimilarity('A fast brown fox', 0.7);
  });

  it('should fail when strings are not semantically similar with custom threshold', async () => {
    await expect('The quick brown fox').not.toMatchSemanticSimilarity(
      'The weather is nice today',
      0.9,
    );
  });
});

const gradingConfig: GradingConfig = {
  provider: 'openai:chat:gpt-4.1-mini',
};

describe('toPassLLMRubric', () => {
  it('should pass when strings meet the LLM Rubric criteria', async () => {
    await expect('Four score and seven years ago').toPassLLMRubric(
      'Contains part of a famous speech',
      gradingConfig,
    );
  });

  it('should fail when strings do not meet the LLM Rubric criteria', async () => {
    await expect('It is time to do laundry').not.toPassLLMRubric(
      'Contains part of a famous speech',
      gradingConfig,
    );
  });
});