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
47 lines
1.6 KiB
YAML
47 lines
1.6 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Vision-language model testing
|
|
|
|
prompts:
|
|
- file://vision_prompt.json
|
|
|
|
providers:
|
|
- id: hyperbolic:Qwen/Qwen2.5-VL-7B-Instruct
|
|
label: Qwen VL 7B
|
|
config:
|
|
temperature: 0.1
|
|
max_tokens: 1024
|
|
|
|
# Note: This model may not be available with your current API key
|
|
# - id: hyperbolic:qwen/Qwen2.5-VL-72B-Instruct
|
|
# label: Qwen VL 72B
|
|
# config:
|
|
# temperature: 0.1
|
|
# max_tokens: 1024
|
|
|
|
# - id: hyperbolic:mistralai/Pixtral-12B
|
|
# label: Pixtral 12B
|
|
# config:
|
|
# temperature: 0.1
|
|
# max_tokens: 1024
|
|
|
|
tests:
|
|
# Animal behavior analysis
|
|
- vars:
|
|
question: 'Describe this adorable creature and what they might be thinking about while munching. Be creative!'
|
|
image_url: 'https://upload.wikimedia.org/wikipedia/commons/thumb/0/0f/Grosser_Panda.JPG/1280px-Grosser_Panda.JPG'
|
|
assert:
|
|
- type: contains-any
|
|
value: ['panda', 'bear', 'bamboo', 'eating']
|
|
- type: llm-rubric
|
|
value: 'The response accurately describes the panda with creative personality insights'
|
|
|
|
# Creative animal storytelling
|
|
- vars:
|
|
question: 'Tell me a short story about what this panda is planning for the weekend. Make it funny!'
|
|
image_url: 'https://upload.wikimedia.org/wikipedia/commons/thumb/0/0f/Grosser_Panda.JPG/1280px-Grosser_Panda.JPG'
|
|
assert:
|
|
- type: contains-any
|
|
value: ['panda', 'weekend', 'bamboo', 'plan']
|
|
- type: llm-rubric
|
|
value: 'The response creates an engaging and humorous story about the panda'
|