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
49 lines
1.4 KiB
YAML
49 lines
1.4 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: 'Groq Provider Demo'
|
|
|
|
prompts:
|
|
- 'Answer this question as concisely as possible: {{calculation}}'
|
|
- 'Calculate the following and provide a brief explanation: {{calculation}}'
|
|
|
|
providers:
|
|
- id: groq:openai/gpt-oss-120b
|
|
label: 'GPT-OSS 120B with tools'
|
|
config:
|
|
max_completion_tokens: 1024
|
|
# gpt-oss is a reasoning model; keep reasoning minimal so the tool call
|
|
# isn't crowded out of the token budget.
|
|
reasoning_effort: 'low'
|
|
tools:
|
|
- type: function
|
|
function:
|
|
name: calculate
|
|
description: 'Evaluate a mathematical expression'
|
|
parameters:
|
|
type: object
|
|
properties:
|
|
expression:
|
|
type: string
|
|
description: 'The mathematical expression to evaluate'
|
|
required:
|
|
- 'expression'
|
|
tool_choice: auto
|
|
- id: groq:openai/gpt-oss-120b
|
|
label: 'GPT-OSS 120B with reasoning'
|
|
config:
|
|
temperature: 0.6
|
|
max_completion_tokens: 1000
|
|
include_reasoning: true
|
|
reasoning_effort: 'medium'
|
|
- id: groq:openai/gpt-oss-20b
|
|
label: 'GPT-OSS 20B (reasoning hidden)'
|
|
config:
|
|
temperature: 0.6
|
|
max_completion_tokens: 1000
|
|
include_reasoning: false
|
|
|
|
tests:
|
|
- vars:
|
|
calculation: 25 * 4 + 10
|
|
- vars:
|
|
calculation: (8 + 2) * 5
|