mirror of
https://github.com/we-promise/sure.git
synced 2026-04-18 19:44:09 +00:00
Add GitHub Actions workflow to discover and run LLM evaluations (#1439)
* Run release eval workflow across model list * Gracefully skip evals when OpenAI token is unusable * Add defensive nil check for eval run export
This commit is contained in:
Juan José Mata
331
.github/workflows/llm-evals.yml
vendored
Normal file
331
.github/workflows/llm-evals.yml
vendored
Normal file
@@ -0,0 +1,331 @@
|
||||
name: LLM Evals
|
||||
|
||||
on:
|
||||
push:
|
||||
tags:
|
||||
- 'v*'
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
env:
|
||||
EVAL_MODELS: gpt-4.1
|
||||
RAILS_ENV: test
|
||||
DATABASE_URL: postgres://postgres:postgres@localhost:5432
|
||||
REDIS_URL: redis://localhost:6379
|
||||
PLAID_CLIENT_ID: foo
|
||||
PLAID_SECRET: bar
|
||||
|
||||
jobs:
|
||||
check_openai:
|
||||
name: Check OpenAI credentials
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
should_run: ${{ steps.gate.outputs.should_run }}
|
||||
reason: ${{ steps.gate.outputs.reason }}
|
||||
|
||||
steps:
|
||||
- name: Validate OpenAI token and quota
|
||||
id: gate
|
||||
env:
|
||||
OPENAI_ACCESS_TOKEN: ${{ secrets.OPENAI_ACCESS_TOKEN }}
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
if [ -z "${OPENAI_ACCESS_TOKEN:-}" ]; then
|
||||
echo "OpenAI token is not configured; skipping eval workflow."
|
||||
echo "should_run=false" >> "$GITHUB_OUTPUT"
|
||||
echo "reason=OPENAI_ACCESS_TOKEN secret is missing" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
TEST_MODEL=$(printf '%s' "$EVAL_MODELS" | cut -d',' -f1 | xargs)
|
||||
if [ -z "$TEST_MODEL" ]; then
|
||||
TEST_MODEL="gpt-4.1"
|
||||
fi
|
||||
|
||||
echo "Checking API access with model: ${TEST_MODEL}"
|
||||
|
||||
RESPONSE_FILE="$(mktemp)"
|
||||
STATUS_CODE=$(curl -sS -o "$RESPONSE_FILE" -w "%{http_code}" \
|
||||
https://api.openai.com/v1/chat/completions \
|
||||
-H "Authorization: Bearer ${OPENAI_ACCESS_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
-d "{\"model\":\"${TEST_MODEL}\",\"messages\":[{\"role\":\"user\",\"content\":\"ping\"}],\"max_tokens\":1}")
|
||||
|
||||
if [ "$STATUS_CODE" = "200" ]; then
|
||||
echo "OpenAI token check passed."
|
||||
echo "should_run=true" >> "$GITHUB_OUTPUT"
|
||||
echo "reason=ok" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
ERROR_MESSAGE=$(ruby -rjson -e '
|
||||
body = File.read(ARGV[0]) rescue ""
|
||||
data = JSON.parse(body) rescue {}
|
||||
message = data.dig("error", "message") || data["message"] || "unknown error"
|
||||
puts message.gsub(/\s+/, " ").strip
|
||||
' "$RESPONSE_FILE")
|
||||
|
||||
echo "OpenAI check failed (${STATUS_CODE}): ${ERROR_MESSAGE}"
|
||||
echo "should_run=false" >> "$GITHUB_OUTPUT"
|
||||
echo "reason=OpenAI token invalid or insufficient quota (${STATUS_CODE})" >> "$GITHUB_OUTPUT"
|
||||
exit 0
|
||||
|
||||
discover_datasets:
|
||||
name: Discover eval datasets
|
||||
needs: check_openai
|
||||
if: needs.check_openai.outputs.should_run == 'true'
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
services:
|
||||
postgres:
|
||||
image: postgres:16
|
||||
env:
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_PASSWORD: postgres
|
||||
ports:
|
||||
- 5432:5432
|
||||
options: --health-cmd="pg_isready" --health-interval=10s --health-timeout=5s --health-retries=3
|
||||
|
||||
redis:
|
||||
image: redis:7.2
|
||||
ports:
|
||||
- 6379:6379
|
||||
options: --health-cmd="redis-cli ping" --health-interval=10s --health-timeout=5s --health-retries=3
|
||||
|
||||
outputs:
|
||||
datasets: ${{ steps.datasets.outputs.datasets }}
|
||||
models: ${{ steps.models.outputs.models }}
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Ruby
|
||||
uses: ruby/setup-ruby@v1
|
||||
with:
|
||||
ruby-version: .ruby-version
|
||||
bundler-cache: true
|
||||
|
||||
- name: Prepare database
|
||||
run: |
|
||||
bin/rails db:create
|
||||
bin/rails db:schema:load
|
||||
|
||||
- name: Import eval datasets
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
shopt -s nullglob
|
||||
dataset_files=(db/eval_data/*.yml)
|
||||
|
||||
if [ ${#dataset_files[@]} -eq 0 ]; then
|
||||
echo "::error::No eval dataset files found under db/eval_data/*.yml"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for dataset_file in "${dataset_files[@]}"; do
|
||||
echo "Importing ${dataset_file}"
|
||||
bundle exec rake "evals:import_dataset[${dataset_file}]"
|
||||
done
|
||||
|
||||
|
||||
- name: Resolve eval models
|
||||
id: models
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
MODELS_JSON=$(bin/rails runner '
|
||||
models = ENV.fetch("EVAL_MODELS", "").split(",").map(&:strip).reject(&:blank?)
|
||||
puts models.to_json
|
||||
')
|
||||
|
||||
if [ "$MODELS_JSON" = "[]" ]; then
|
||||
echo "::error::EVAL_MODELS is empty. Set at least one model, for example: EVAL_MODELS=gpt-4.1"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
{
|
||||
echo "models<<EOF"
|
||||
echo "$MODELS_JSON"
|
||||
echo "EOF"
|
||||
} >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Resolve available eval datasets
|
||||
id: datasets
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
DATASETS_JSON=$(bin/rails runner 'puts Eval::Dataset.order(:name).pluck(:name).to_json')
|
||||
|
||||
if [ "$DATASETS_JSON" = "[]" ]; then
|
||||
echo "::error::No eval datasets found. Import one first with: rake evals:import_dataset[path/to/file.yml]"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
{
|
||||
echo "datasets<<EOF"
|
||||
echo "$DATASETS_JSON"
|
||||
echo "EOF"
|
||||
} >> "$GITHUB_OUTPUT"
|
||||
|
||||
run_evals:
|
||||
name: Run eval for ${{ matrix.dataset }} on ${{ matrix.model }}
|
||||
needs: [check_openai, discover_datasets]
|
||||
if: needs.check_openai.outputs.should_run == 'true'
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
dataset: ${{ fromJson(needs.discover_datasets.outputs.datasets) }}
|
||||
model: ${{ fromJson(needs.discover_datasets.outputs.models) }}
|
||||
|
||||
services:
|
||||
postgres:
|
||||
image: postgres:16
|
||||
env:
|
||||
POSTGRES_USER: postgres
|
||||
POSTGRES_PASSWORD: postgres
|
||||
ports:
|
||||
- 5432:5432
|
||||
options: --health-cmd="pg_isready" --health-interval=10s --health-timeout=5s --health-retries=3
|
||||
|
||||
redis:
|
||||
image: redis:7.2
|
||||
ports:
|
||||
- 6379:6379
|
||||
options: --health-cmd="redis-cli ping" --health-interval=10s --health-timeout=5s --health-retries=3
|
||||
|
||||
steps:
|
||||
- name: Checkout code
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Set up Ruby
|
||||
uses: ruby/setup-ruby@v1
|
||||
with:
|
||||
ruby-version: .ruby-version
|
||||
bundler-cache: true
|
||||
|
||||
- name: Prepare database
|
||||
run: |
|
||||
bin/rails db:create
|
||||
bin/rails db:schema:load
|
||||
|
||||
- name: Import eval datasets
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
shopt -s nullglob
|
||||
dataset_files=(db/eval_data/*.yml)
|
||||
|
||||
if [ ${#dataset_files[@]} -eq 0 ]; then
|
||||
echo "::error::No eval dataset files found under db/eval_data/*.yml"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
for dataset_file in "${dataset_files[@]}"; do
|
||||
echo "Importing ${dataset_file}"
|
||||
bundle exec rake "evals:import_dataset[${dataset_file}]"
|
||||
done
|
||||
|
||||
- name: Prepare dataset artifact names
|
||||
id: dataset_slug
|
||||
env:
|
||||
DATASET: ${{ matrix.dataset }}
|
||||
MODEL: ${{ matrix.model }}
|
||||
shell: bash
|
||||
run: |
|
||||
set -euo pipefail
|
||||
|
||||
slug=$(printf '%s' "$DATASET" \
|
||||
| tr '[:upper:]' '[:lower:]' \
|
||||
| sed -E 's/[^a-z0-9]+/-/g; s/^-+//; s/-+$//; s/-{2,}/-/g')
|
||||
|
||||
if [ -z "$slug" ]; then
|
||||
echo "::error::Could not generate dataset slug from '$DATASET'"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "slug=$slug" >> "$GITHUB_OUTPUT"
|
||||
model_slug=$(printf '%s' "$MODEL" \
|
||||
| tr '[:upper:]' '[:lower:]' \
|
||||
| sed -E 's/[^a-z0-9]+/-/g; s/^-+//; s/-+$//; s/-{2,}/-/g')
|
||||
|
||||
if [ -z "$model_slug" ]; then
|
||||
echo "::error::Could not generate model slug from '$MODEL'"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "model_slug=$model_slug" >> "$GITHUB_OUTPUT"
|
||||
echo "log_path=tmp/evals/${slug}-${model_slug}.log" >> "$GITHUB_OUTPUT"
|
||||
echo "json_path=tmp/evals/${slug}-${model_slug}.json" >> "$GITHUB_OUTPUT"
|
||||
|
||||
- name: Verify dataset exists
|
||||
env:
|
||||
DATASET: ${{ matrix.dataset }}
|
||||
MODEL: ${{ matrix.model }}
|
||||
run: |
|
||||
bin/rails runner 'dataset = Eval::Dataset.find_by(name: ENV.fetch("DATASET")); abort("Dataset not found: #{ENV.fetch("DATASET")}") if dataset.nil?'
|
||||
|
||||
- name: Run eval
|
||||
env:
|
||||
DATASET: ${{ matrix.dataset }}
|
||||
MODEL: ${{ matrix.model }}
|
||||
OPENAI_ACCESS_TOKEN: ${{ secrets.OPENAI_ACCESS_TOKEN }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
mkdir -p tmp/evals
|
||||
bundle exec rake "evals:run[${DATASET},${MODEL}]" | tee "${{ steps.dataset_slug.outputs.log_path }}"
|
||||
|
||||
- name: Export run summary
|
||||
env:
|
||||
DATASET: ${{ matrix.dataset }}
|
||||
MODEL: ${{ matrix.model }}
|
||||
run: |
|
||||
bin/rails runner '
|
||||
dataset = Eval::Dataset.find_by!(name: ENV.fetch("DATASET"))
|
||||
run = Eval::Run.where(dataset: dataset, model: ENV.fetch("MODEL")).order(created_at: :desc).first
|
||||
abort("No eval run found for dataset #{dataset.name} and model #{ENV.fetch("MODEL")}") if run.nil?
|
||||
payload = {
|
||||
dataset: dataset.name,
|
||||
dataset_metadata: dataset.metadata,
|
||||
model: ENV.fetch("MODEL"),
|
||||
run_id: run.id,
|
||||
status: run.status,
|
||||
created_at: run.created_at,
|
||||
completed_at: run.completed_at,
|
||||
total_prompt_tokens: run.total_prompt_tokens,
|
||||
total_completion_tokens: run.total_completion_tokens,
|
||||
total_cost: run.total_cost,
|
||||
metrics: run.metrics
|
||||
}
|
||||
File.write("${{ steps.dataset_slug.outputs.json_path }}", JSON.pretty_generate(payload))
|
||||
'
|
||||
|
||||
- name: Upload eval artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: llm-evals-${{ steps.dataset_slug.outputs.slug }}-${{ steps.dataset_slug.outputs.model_slug }}
|
||||
path: |
|
||||
${{ steps.dataset_slug.outputs.log_path }}
|
||||
${{ steps.dataset_slug.outputs.json_path }}
|
||||
if-no-files-found: error
|
||||
retention-days: 30
|
||||
|
||||
skip_evals:
|
||||
name: Skip evals (no valid OpenAI token/quota)
|
||||
needs: check_openai
|
||||
if: needs.check_openai.outputs.should_run != 'true'
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Report skip reason
|
||||
run: |
|
||||
echo "LLM evals were skipped gracefully."
|
||||
echo "Reason: ${{ needs.check_openai.outputs.reason }}"
|
||||
Reference in New Issue
Block a user