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 +1,96 @@
|
||||
# config-structured-outputs (Multi-Provider Structured Outputs)
|
||||
|
||||
You can run this example with:
|
||||
|
||||
```bash
|
||||
npx promptfoo@latest init --example config-structured-outputs
|
||||
cd config-structured-outputs
|
||||
```
|
||||
|
||||
This example demonstrates how to enforce structured JSON outputs using schema validation across multiple AI providers:
|
||||
|
||||
- **OpenAI** - using `response_format` with `json_schema`
|
||||
- **Azure OpenAI** - using `response_format` with `json_schema`
|
||||
- **Anthropic** - using `output_format` with `json_schema`
|
||||
|
||||
The example includes two prompt configurations for solving quirky math problems:
|
||||
|
||||
- One that requires step-by-step problem solving (with `steps` array)
|
||||
- One that only requires the final answer (without `steps` array)
|
||||
|
||||
## Environment Variables
|
||||
|
||||
This example requires at least one of the following API keys:
|
||||
|
||||
- `OPENAI_API_KEY` - Your OpenAI API key for testing with GPT models
|
||||
- `ANTHROPIC_API_KEY` - Your Anthropic API key for testing with Claude models
|
||||
- For Azure OpenAI: See [Azure OpenAI provider docs](https://promptfoo.dev/docs/providers/azure) for required credentials
|
||||
|
||||
You can set these in a `.env` file or directly in your environment:
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY=your_api_key_here
|
||||
export ANTHROPIC_API_KEY=your_api_key_here
|
||||
```
|
||||
|
||||
## Provider Differences
|
||||
|
||||
### OpenAI/Azure Format
|
||||
|
||||
OpenAI and Azure use `response_format` at the prompt level:
|
||||
|
||||
```yaml
|
||||
prompts:
|
||||
- raw: 'Your prompt here'
|
||||
config:
|
||||
response_format:
|
||||
type: json_schema
|
||||
json_schema:
|
||||
name: schema_name
|
||||
strict: true
|
||||
schema:
|
||||
# Your schema here
|
||||
```
|
||||
|
||||
### Anthropic Format
|
||||
|
||||
Anthropic uses `output_format` at the provider level:
|
||||
|
||||
```yaml
|
||||
providers:
|
||||
- id: anthropic:messages:claude-sonnet-4-6
|
||||
config:
|
||||
output_format:
|
||||
type: json_schema
|
||||
schema:
|
||||
# Your schema here (no nested json_schema object)
|
||||
```
|
||||
|
||||
## Getting Started
|
||||
|
||||
1. Review and customize `promptfooconfig.yaml` as needed
|
||||
2. Remove any providers you don't have API keys for
|
||||
3. Run the evaluation:
|
||||
|
||||
```bash
|
||||
promptfoo eval
|
||||
```
|
||||
|
||||
4. View the results:
|
||||
|
||||
```bash
|
||||
promptfoo view
|
||||
```
|
||||
|
||||
## What You'll Learn
|
||||
|
||||
- How to enforce JSON schemas across different providers
|
||||
- The syntax differences between OpenAI and Anthropic structured outputs
|
||||
- How to validate that responses are always valid JSON objects
|
||||
- How to require specific fields and types in LLM responses
|
||||
|
||||
## Learn More
|
||||
|
||||
- [OpenAI Structured Outputs Documentation](https://platform.openai.com/docs/guides/structured-outputs)
|
||||
- [Anthropic Structured Outputs Documentation](https://docs.anthropic.com/en/docs/build-with-claude/structured-outputs)
|
||||
- [promptfoo Structured Outputs Guide](https://promptfoo.dev/docs/)
|
||||
@@ -0,0 +1,136 @@
|
||||
# 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'
|
||||
Reference in New Issue
Block a user