Skip to content

Evals

Evals #18

Workflow file for this run

name: Run Braintrust Evals
on:
workflow_dispatch:
pull_request:
permissions:
write-all
jobs:
eval:
name: Run evals
runs-on: ubuntu-latest
permissions: write-all
env:
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
SUPABASE_KEY: ${{ secrets.SUPABASE_KEY }}
VOYAGEAI_API_KEY: ${{ secrets.VOYAGEAI_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
UBIQUITY_OS_APP_NAME: ${{ secrets.UBIQUITY_OS_APP_NAME }}
steps:
- uses: actions/setup-node@v4
with:
node-version: "20.10.0"
- uses: actions/checkout@master
with:
fetch-depth: 0
- name: Install Dependencies
id: install
run: yarn install --immutable --immutable-cache --check-cache
- name: Run Evals
id: evals
run: yarn eval
env:
SUPABASE_URL: ${{ secrets.SUPABASE_URL }}
SUPABASE_KEY: ${{ secrets.SUPABASE_KEY }}
VOYAGEAI_API_KEY: ${{ secrets.VOYAGEAI_API_KEY }}
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
OPENROUTER_API_KEY: ${{ secrets.OPENROUTER_API_KEY }}
UBIQUITY_OS_APP_NAME: ${{ secrets.UBIQUITY_OS_APP_NAME }}
- name: Add Evals Report to Github Comment
if: always()
run: echo "$(cat llm.evals.md)" >> $GITHUB_STEP_SUMMARY