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
88 lines
2.6 KiB
YAML
88 lines
2.6 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: IMDB Review Sentiment Analysis
|
|
|
|
providers:
|
|
- openai:gpt-4.1-mini
|
|
|
|
prompts:
|
|
- label: Sentiment Analysis
|
|
raw: |
|
|
Analyze the sentiment of the following movie review. Classify it as either positive or negative.
|
|
|
|
Review: "{{text}}"
|
|
|
|
Respond with a JSON object in the following format:
|
|
{
|
|
"sentiment": "positive" or "negative",
|
|
"confidence": number between 1-10,
|
|
"reasoning": "brief explanation"
|
|
}
|
|
config:
|
|
response_format:
|
|
type: json_schema
|
|
json_schema:
|
|
name: MovieReviewSentiment
|
|
schema:
|
|
type: object
|
|
properties:
|
|
sentiment:
|
|
type: string
|
|
enum: ['positive', 'negative']
|
|
confidence:
|
|
type: integer
|
|
minimum: 1
|
|
maximum: 10
|
|
reasoning:
|
|
type: string
|
|
required: ['sentiment', 'confidence', 'reasoning']
|
|
|
|
defaultTest:
|
|
assert:
|
|
# Basic JSON validation
|
|
- type: is-json
|
|
|
|
# Track binary classification metrics
|
|
- type: javascript
|
|
value: 'output.sentiment === context.vars.sentiment'
|
|
metric: accuracy
|
|
|
|
# For F1 score components (treating 'positive' as the positive class)
|
|
- type: javascript
|
|
value: "output.sentiment === 'positive' && context.vars.sentiment === 'positive' ? 1 : 0"
|
|
metric: true_positives
|
|
weight: 0
|
|
|
|
- type: javascript
|
|
value: "output.sentiment === 'positive' && context.vars.sentiment === 'negative' ? 1 : 0"
|
|
metric: false_positives
|
|
weight: 0
|
|
|
|
- type: javascript
|
|
value: "output.sentiment === 'negative' && context.vars.sentiment === 'positive' ? 1 : 0"
|
|
metric: false_negatives
|
|
weight: 0
|
|
|
|
- type: javascript
|
|
value: "output.sentiment === 'negative' && context.vars.sentiment === 'negative' ? 1 : 0"
|
|
metric: true_negatives
|
|
weight: 0
|
|
|
|
derivedMetrics:
|
|
# Precision = TP / (TP + FP)
|
|
- name: precision
|
|
value: true_positives / (true_positives + false_positives)
|
|
|
|
# Recall = TP / (TP + FN)
|
|
- name: recall
|
|
value: true_positives / (true_positives + false_negatives)
|
|
|
|
# F1 Score = 2 * (precision * recall) / (precision + recall)
|
|
- name: f1_score
|
|
value: 2 * true_positives / (2 * true_positives + false_positives + false_negatives)
|
|
|
|
# Accuracy = (TP + TN) / (TP + TN + FP + FN)
|
|
- name: accuracy_score
|
|
value: (true_positives + true_negatives) / (true_positives + true_negatives + false_positives + false_negatives)
|
|
|
|
tests: file://imdb_eval_sample.csv
|