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
111 lines
2.9 KiB
YAML
111 lines
2.9 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: 'Bedrock Nova Tool Use Eval'
|
|
|
|
prompts:
|
|
- 'What is the color of {{topic}}? ONLY answer using the "color_json" tool.'
|
|
|
|
providers:
|
|
- id: bedrock:amazon.nova-micro-v1:0
|
|
config:
|
|
region: 'us-east-1'
|
|
inferenceConfig:
|
|
temperature: 0.7
|
|
max_new_tokens: 256
|
|
toolConfig:
|
|
toolChoice:
|
|
auto: {}
|
|
tools:
|
|
- toolSpec:
|
|
name: color_json
|
|
description: 'Outputs the color of a thing'
|
|
inputSchema:
|
|
json:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description: 'The name of the thing'
|
|
color:
|
|
type: string
|
|
description: 'The color of the thing'
|
|
required:
|
|
- name
|
|
- color
|
|
- id: bedrock:amazon.nova-lite-v1:0
|
|
config:
|
|
region: 'us-east-1'
|
|
inferenceConfig:
|
|
temperature: 0.7
|
|
max_new_tokens: 256
|
|
toolConfig:
|
|
toolChoice:
|
|
auto: {}
|
|
tools:
|
|
- toolSpec:
|
|
name: color_json
|
|
description: 'Outputs the color of a thing'
|
|
inputSchema:
|
|
json:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description: 'The name of the thing'
|
|
color:
|
|
type: string
|
|
description: 'The color of the thing'
|
|
required:
|
|
- name
|
|
- color
|
|
- id: bedrock:amazon.nova-pro-v1:0
|
|
config:
|
|
region: 'us-east-1'
|
|
inferenceConfig:
|
|
temperature: 0.7
|
|
max_new_tokens: 256
|
|
toolConfig:
|
|
toolChoice:
|
|
auto: {}
|
|
tools:
|
|
- toolSpec:
|
|
name: color_json
|
|
description: 'Outputs the color of a thing'
|
|
inputSchema:
|
|
json:
|
|
type: object
|
|
properties:
|
|
name:
|
|
type: string
|
|
description: 'The name of the thing'
|
|
color:
|
|
type: string
|
|
description: 'The color of the thing'
|
|
required:
|
|
- name
|
|
- color
|
|
|
|
defaultTest:
|
|
options:
|
|
transform: 'JSON.parse(output).input.color'
|
|
tests:
|
|
- vars:
|
|
topic: sky
|
|
assert:
|
|
- type: equals
|
|
value: blue
|
|
- vars:
|
|
topic: ocean
|
|
assert:
|
|
- type: equals
|
|
value: blue
|
|
- vars:
|
|
topic: banana
|
|
assert:
|
|
- type: equals
|
|
value: yellow
|
|
- vars:
|
|
topic: grass
|
|
assert:
|
|
- type: equals
|
|
value: green
|