chore: import upstream snapshot with attribution
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
This commit is contained in:
@@ -0,0 +1,209 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import { handleAnswerRelevance } from '../../src/assertions/answerRelevance';
|
||||
import { matchesAnswerRelevance } from '../../src/matchers/rag';
|
||||
import invariant from '../../src/util/invariant';
|
||||
|
||||
import type { AssertionValueFunctionContext } from '../../src/types/index';
|
||||
|
||||
vi.mock('../../src/matchers/rag');
|
||||
vi.mock('../../src/util/invariant');
|
||||
|
||||
describe('handleAnswerRelevance', () => {
|
||||
beforeEach(() => {
|
||||
vi.resetAllMocks();
|
||||
vi.mocked(invariant).mockImplementation((condition, message) => {
|
||||
if (!condition) {
|
||||
throw new Error(typeof message === 'function' ? message() : message);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
it('should call matchesAnswerRelevance with correct parameters', async () => {
|
||||
const mockMatchesAnswerRelevance = vi.mocked(matchesAnswerRelevance);
|
||||
mockMatchesAnswerRelevance.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
|
||||
const result = await handleAnswerRelevance({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
threshold: 0.7,
|
||||
},
|
||||
output: 'test output',
|
||||
prompt: 'test prompt',
|
||||
test: {
|
||||
vars: {},
|
||||
options: {},
|
||||
},
|
||||
baseType: 'answer-relevance',
|
||||
assertionValueContext: {} as AssertionValueFunctionContext,
|
||||
inverse: false,
|
||||
outputString: 'test output',
|
||||
providerResponse: {
|
||||
output: 'test output',
|
||||
tokenUsage: {},
|
||||
},
|
||||
});
|
||||
|
||||
expect(mockMatchesAnswerRelevance).toHaveBeenCalledWith(
|
||||
'test prompt',
|
||||
'test output',
|
||||
0.7,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
expect(result).toEqual({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
threshold: 0.7,
|
||||
},
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
});
|
||||
|
||||
it('should use query from vars if available', async () => {
|
||||
const mockMatchesAnswerRelevance = vi.mocked(matchesAnswerRelevance);
|
||||
mockMatchesAnswerRelevance.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
|
||||
const result = await handleAnswerRelevance({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
threshold: 0.7,
|
||||
},
|
||||
output: 'test output',
|
||||
prompt: 'test prompt',
|
||||
test: {
|
||||
vars: {
|
||||
query: 'test query',
|
||||
},
|
||||
options: {},
|
||||
},
|
||||
baseType: 'answer-relevance',
|
||||
assertionValueContext: {} as AssertionValueFunctionContext,
|
||||
inverse: false,
|
||||
outputString: 'test output',
|
||||
providerResponse: {
|
||||
output: 'test output',
|
||||
tokenUsage: {},
|
||||
},
|
||||
});
|
||||
|
||||
expect(mockMatchesAnswerRelevance).toHaveBeenCalledWith(
|
||||
'test query',
|
||||
'test output',
|
||||
0.7,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
expect(result).toEqual({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
threshold: 0.7,
|
||||
},
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
});
|
||||
|
||||
it('should throw error if output is not string', async () => {
|
||||
await expect(
|
||||
handleAnswerRelevance({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
},
|
||||
output: {},
|
||||
prompt: 'test prompt',
|
||||
test: {
|
||||
vars: {},
|
||||
options: {},
|
||||
},
|
||||
baseType: 'answer-relevance',
|
||||
assertionValueContext: {} as AssertionValueFunctionContext,
|
||||
inverse: false,
|
||||
outputString: 'test output',
|
||||
providerResponse: {
|
||||
output: 'test output',
|
||||
tokenUsage: {},
|
||||
},
|
||||
}),
|
||||
).rejects.toThrow('answer-relevance assertion type must evaluate a string output');
|
||||
});
|
||||
|
||||
it('should throw error if prompt is missing', async () => {
|
||||
await expect(
|
||||
handleAnswerRelevance({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
},
|
||||
output: 'test output',
|
||||
prompt: '',
|
||||
test: {
|
||||
vars: {},
|
||||
options: {},
|
||||
},
|
||||
baseType: 'answer-relevance',
|
||||
assertionValueContext: {} as AssertionValueFunctionContext,
|
||||
inverse: false,
|
||||
outputString: 'test output',
|
||||
providerResponse: {
|
||||
output: 'test output',
|
||||
tokenUsage: {},
|
||||
},
|
||||
}),
|
||||
).rejects.toThrow('answer-relevance assertion type must have a prompt');
|
||||
});
|
||||
|
||||
it('should use default threshold of 0 if not specified', async () => {
|
||||
const mockMatchesAnswerRelevance = vi.mocked(matchesAnswerRelevance);
|
||||
mockMatchesAnswerRelevance.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
|
||||
const result = await handleAnswerRelevance({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
},
|
||||
output: 'test output',
|
||||
prompt: 'test prompt',
|
||||
test: {
|
||||
vars: {},
|
||||
options: {},
|
||||
},
|
||||
baseType: 'answer-relevance',
|
||||
assertionValueContext: {} as AssertionValueFunctionContext,
|
||||
inverse: false,
|
||||
outputString: 'test output',
|
||||
providerResponse: {
|
||||
output: 'test output',
|
||||
tokenUsage: {},
|
||||
},
|
||||
});
|
||||
|
||||
expect(mockMatchesAnswerRelevance).toHaveBeenCalledWith(
|
||||
'test prompt',
|
||||
'test output',
|
||||
0,
|
||||
{},
|
||||
undefined,
|
||||
);
|
||||
expect(result).toEqual({
|
||||
assertion: {
|
||||
type: 'answer-relevance',
|
||||
},
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'test reason',
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user