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
137 lines
3.8 KiB
YAML
137 lines
3.8 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Multi-provider structured JSON outputs with schema validation
|
|
|
|
prompts:
|
|
# Schema output with `steps` array
|
|
- label: 'With step-by-step'
|
|
raw: 'You are a helpful math tutor. Solve {{problem}}'
|
|
config:
|
|
response_format:
|
|
type: json_schema
|
|
json_schema:
|
|
name: math_response
|
|
strict: true
|
|
schema:
|
|
type: object
|
|
properties:
|
|
steps:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
explanation:
|
|
type: string
|
|
output:
|
|
type: string
|
|
required:
|
|
- explanation
|
|
- output
|
|
additionalProperties: false
|
|
final_answer:
|
|
type: string
|
|
required:
|
|
- steps
|
|
- final_answer
|
|
additionalProperties: false
|
|
|
|
# Schema output without `steps` array
|
|
- label: 'Without step-by-step'
|
|
raw: 'You are a helpful math tutor. Solve {{problem}}'
|
|
config:
|
|
response_format:
|
|
type: json_schema
|
|
json_schema:
|
|
name: math_response
|
|
strict: true
|
|
schema:
|
|
type: object
|
|
properties:
|
|
final_answer:
|
|
type: string
|
|
required:
|
|
- final_answer
|
|
additionalProperties: false
|
|
|
|
providers:
|
|
# OpenAI with structured outputs (response_format)
|
|
- openai:chat:gpt-4o-mini
|
|
|
|
# Azure OpenAI with structured outputs (response_format)
|
|
- id: azure:chat:gpt-4o-2024-08-06
|
|
config:
|
|
apiHost: 'YOUR_ORG.openai.azure.com'
|
|
apiVersion: '2024-08-01-preview'
|
|
deploymentName: 'YOUR_DEPLOYMENT_NAME'
|
|
|
|
# Anthropic with structured outputs (output_format) - with steps
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
label: 'Anthropic (with steps)'
|
|
config:
|
|
max_tokens: 2048
|
|
output_format:
|
|
type: json_schema
|
|
schema:
|
|
type: object
|
|
properties:
|
|
steps:
|
|
type: array
|
|
items:
|
|
type: object
|
|
properties:
|
|
explanation:
|
|
type: string
|
|
output:
|
|
type: string
|
|
required:
|
|
- explanation
|
|
- output
|
|
additionalProperties: false
|
|
final_answer:
|
|
type: string
|
|
required:
|
|
- steps
|
|
- final_answer
|
|
additionalProperties: false
|
|
|
|
# Anthropic with structured outputs (output_format) - without steps
|
|
- id: anthropic:messages:claude-sonnet-4-6
|
|
label: 'Anthropic (without steps)'
|
|
config:
|
|
max_tokens: 2048
|
|
output_format:
|
|
type: json_schema
|
|
schema:
|
|
type: object
|
|
properties:
|
|
final_answer:
|
|
type: string
|
|
required:
|
|
- final_answer
|
|
additionalProperties: false
|
|
|
|
defaultTest:
|
|
assert:
|
|
- type: is-json
|
|
- type: javascript
|
|
value: typeof output === 'object'
|
|
|
|
tests:
|
|
- description: Solving for the number of dragons in a cave
|
|
vars:
|
|
problem: 'If a wizard has 8x dragons and finds 31 more in a cave, but only has room for 2 total, how many dragons must the wizard release? (8x + 31 = 2)'
|
|
assert:
|
|
- type: contains-any
|
|
value:
|
|
- -3.625
|
|
- -29/8
|
|
- '-3.625'
|
|
- '-29/8'
|
|
- description: Calculating the area of a perfectly square pizza
|
|
vars:
|
|
problem: 'A perfectly square pizza has a side length of sqrt(x) meters. If the side length is 4.9 meters, what is the area in square meters? (sqrt(x) = 4.9)'
|
|
assert:
|
|
- type: contains-any
|
|
value:
|
|
- 24.01
|
|
- '24.01'
|