chore: import upstream snapshot with attribution
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Waiting to run
Test and Publish Multi-arch Docker Image / test (push) Waiting to run
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Blocked by required conditions
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) Blocked by required conditions
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Blocked by required conditions
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Blocked by required conditions
Validate Renovate Config / Validate Renovate Configuration (push) Waiting to run
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) Waiting to run
Test and Publish Multi-arch Docker Image / test (push) Waiting to run
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Blocked by required conditions
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) Blocked by required conditions
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Blocked by required conditions
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Blocked by required conditions
Validate Renovate Config / Validate Renovate Configuration (push) Waiting to run
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
This commit is contained in:
@@ -0,0 +1,22 @@
|
||||
# eval-javascript-assert-external (Javascript Assert External)
|
||||
|
||||
You can run this example with:
|
||||
|
||||
```bash
|
||||
npx promptfoo@latest init --example eval-javascript-assert-external
|
||||
cd eval-javascript-assert-external
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
To get started, set your OPENAI_API_KEY environment variable.
|
||||
|
||||
Next, edit assert.js and promptfooconfig.yaml.
|
||||
|
||||
Then run:
|
||||
|
||||
```bash
|
||||
promptfoo eval
|
||||
```
|
||||
|
||||
Afterwards, you can view the results by running `promptfoo view`
|
||||
@@ -0,0 +1,46 @@
|
||||
module.exports = {
|
||||
customFunction: (output, context) => {
|
||||
console.log('Prompt:', context.prompt);
|
||||
console.log('Vars', context.vars.topic);
|
||||
|
||||
// You can return a bool...
|
||||
// return output.toLowerCase().includes('bananas');
|
||||
|
||||
// A score (where 0 = Fail)...
|
||||
// return 0.5;
|
||||
|
||||
// Or an entire grading result, which can be simple...
|
||||
// return {
|
||||
// pass: output.toLowerCase().includes('bananas'),
|
||||
// score: 0.5,
|
||||
// reason: 'Contains banana',
|
||||
// };
|
||||
|
||||
// Or include nested assertions...
|
||||
const result = {
|
||||
pass: true,
|
||||
score: 0.75,
|
||||
reason: 'Looks good to me',
|
||||
componentResults: [
|
||||
{
|
||||
pass: output.toLowerCase().includes('bananas'),
|
||||
score: 0.5,
|
||||
reason: 'Contains banana',
|
||||
namedScores: {
|
||||
'Uses banana': 1.0,
|
||||
},
|
||||
},
|
||||
{
|
||||
pass: output.toLowerCase().includes('yellow'),
|
||||
score: 0.5,
|
||||
reason: 'Contains yellow',
|
||||
namedScores: {
|
||||
Yellowish: 0.66,
|
||||
},
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
return result;
|
||||
},
|
||||
};
|
||||
@@ -0,0 +1,25 @@
|
||||
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
||||
description: External JavaScript assertion files for custom validation
|
||||
|
||||
prompts:
|
||||
- 'Tell me about {{topic}} in three words'
|
||||
|
||||
providers:
|
||||
- openai:gpt-4o
|
||||
|
||||
defaultTest:
|
||||
assert:
|
||||
- type: javascript
|
||||
value: file://assert.js:customFunction
|
||||
config:
|
||||
foo: bar
|
||||
|
||||
tests:
|
||||
- vars:
|
||||
topic: yellow fruits
|
||||
- vars:
|
||||
topic: fruits high in potassium
|
||||
- vars:
|
||||
topic: fruits that are long and skinny
|
||||
- vars:
|
||||
topic: fruits that smell bad
|
||||
Reference in New Issue
Block a user