wehub-resource-sync
0d3cb498a3
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
46 lines
1.3 KiB
YAML
46 lines
1.3 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: PydanticAI agent evaluation
|
|
|
|
prompts:
|
|
- '{{query}}'
|
|
|
|
providers:
|
|
- id: file://provider.py
|
|
label: PydanticAI Weather Agent
|
|
|
|
defaultTest:
|
|
assert:
|
|
- type: is-json
|
|
value:
|
|
type: object
|
|
properties:
|
|
location:
|
|
type: string
|
|
temperature:
|
|
type: string
|
|
description:
|
|
type: string
|
|
required: ['location', 'temperature', 'description']
|
|
|
|
tests:
|
|
- description: 'Basic weather query with JavaScript assertion'
|
|
vars:
|
|
query: "What's the weather like in London?"
|
|
assert:
|
|
- type: javascript
|
|
value: output.location.toLowerCase().includes('london') && output.temperature !== 'N/A'
|
|
|
|
- description: 'Structured output validation with Python assertion'
|
|
vars:
|
|
query: 'Weather in New York'
|
|
assert:
|
|
- type: python
|
|
value: "'new york' in output.get('location', '').lower() and output.get('temperature', '').endswith(('°C', '°F'))"
|
|
|
|
- description: 'Weather quality assessment with LLM rubric'
|
|
vars:
|
|
query: 'Weather in Tokyo'
|
|
assert:
|
|
- type: llm-rubric
|
|
value: 'The weather response should be realistic and include proper temperature units. The location should be correctly identified as Tokyo.'
|