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
65 lines
1.9 KiB
YAML
65 lines
1.9 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
|
|
description: 'Evaluation of Llama vision models for e-commerce product analysis'
|
|
|
|
prompts:
|
|
- label: 'Product Description'
|
|
raw: |
|
|
Analyze this product image and provide a detailed description suitable for an e-commerce listing:
|
|
[Image]({{image_url}})
|
|
|
|
- label: 'Quality Check'
|
|
raw: |
|
|
Review this product image and identify any issues that would make it unsuitable for an e-commerce listing:
|
|
1. Image quality (blur, lighting, resolution)
|
|
2. Background and presentation
|
|
3. Product visibility and completeness
|
|
[Image]({{image_url}})
|
|
|
|
providers:
|
|
- id: vertex:llama-3.2-90b-vision-instruct-maas
|
|
config:
|
|
generationConfig:
|
|
temperature: 0.7
|
|
maxOutputTokens: 1024
|
|
context: 'You are a professional e-commerce product photographer and quality assurance specialist.'
|
|
extra_body:
|
|
google:
|
|
model_safety_settings:
|
|
enabled: true
|
|
llama_guard_settings: {}
|
|
|
|
tests:
|
|
- description: Test with good product image
|
|
vars:
|
|
image_url: 'https://storage.googleapis.com/vertex-ai-samples/product-images/coffee-mug-white.jpg'
|
|
assert:
|
|
- type: contains-all
|
|
value:
|
|
- 'resolution'
|
|
- 'lighting'
|
|
- 'background'
|
|
- type: contains-any
|
|
value:
|
|
- 'high quality'
|
|
- 'clear'
|
|
- 'well-lit'
|
|
- type: not-contains-any
|
|
value:
|
|
- 'blurry'
|
|
- 'poor quality'
|
|
- 'unclear'
|
|
|
|
- description: Test with poor quality image
|
|
vars:
|
|
image_url: 'https://storage.googleapis.com/vertex-ai-samples/product-images/coffee-mug-blurry.jpg'
|
|
assert:
|
|
- type: contains-any
|
|
value:
|
|
- 'blurry'
|
|
- 'poor lighting'
|
|
- 'low resolution'
|
|
- 'unclear'
|
|
- type: contains
|
|
value: 'improvement'
|