promptfoo--promptfoo
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
50 行
1.5 KiB
YAML
50 行
1.5 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
||
description: Function calling with Llama 4 for mathematical problem solving
|
||
prompts:
|
||
- file://tool_prompts.txt
|
||
providers:
|
||
- id: cerebras:llama-4-scout-17b-16e-instruct
|
||
config:
|
||
temperature: 0.7
|
||
max_completion_tokens: 1024
|
||
tools:
|
||
- type: 'function'
|
||
function:
|
||
name: 'calculate'
|
||
description: 'A calculator that can perform basic arithmetic operations'
|
||
parameters:
|
||
type: 'object'
|
||
properties:
|
||
expression:
|
||
type: 'string'
|
||
description: 'The mathematical expression to evaluate'
|
||
required: ['expression']
|
||
strict: true
|
||
tests:
|
||
- vars:
|
||
problem: '15 × 7'
|
||
explanation: 'the product of fifteen and seven'
|
||
assert:
|
||
- type: contains
|
||
value: '105'
|
||
- type: contains-any
|
||
value: ['multiply', 'multiplication', 'multiplying', 'product']
|
||
- vars:
|
||
problem: '(42 × 3) ÷ 6'
|
||
explanation: 'forty-two times three, divided by six'
|
||
assert:
|
||
- type: contains
|
||
value: '21'
|
||
- type: contains-any
|
||
value: ['order of operations', 'PEMDAS', 'parentheses', 'brackets']
|
||
- vars:
|
||
problem: '√(144) + 25²'
|
||
explanation: 'the square root of one hundred forty-four plus twenty-five squared'
|
||
assert:
|
||
- type: contains
|
||
value: '637'
|
||
- type: contains-any
|
||
value: ['square root', 'exponent', 'power', 'squared']
|
||
outputs:
|
||
- type: text
|