gen-ai-evaluation-toolkit-on-aws / python-api
CLAUDE.md21 starsChanged 4 months agoApache-2.0View on GitHub
Lambda REST API for the evaluation toolkit. Tests support dual mode: onebox (moto mocks, default) and e2e (real AWS).
In this repositoryOne other file it gives its agents.
- packages/evaluator-sdk/CLAUDE.mdCLAUDE.md
The file
Files
python-api
Lambda REST API for the evaluation toolkit.
Structure
src/evaluator_api/
├── handler.py # Lambda entry point
├── routes/
│ ├── __init__.py # App, DAOs, init_aws, exceptions
│ ├── evaluator_jobs.py
│ ├── reports.py
│ ├── results.py
│ └── models.py # Pydantic route models
└── ddb/
├── __init__.py
├── dao.py # DynamoDB DAOs
└── models.py # DynamoDB Pydantic modelsCommands
uv sync --dev # Install deps
uv run pytest tests --cov=evaluator_api --cov-report=term # Run tests
uv run ruff check src tests # Lint
uv run mypy src # Type checkKey Patterns
- DAO pattern for DDB operations
- Pydantic models separate for API vs persistence
- Concurrent score writes use
SET #scores.#score_name = :value
E2E Testing
Tests support dual mode: onebox (moto mocks, default) and e2e (real AWS).
Required env vars for e2e
ETK_API_ENDPOINT— API Gateway URL (e.g.https://abc123.execute-api.eu-west-2.amazonaws.com/prod)ETK_AWS_REGION— AWS region (default:us-east-1)
Running e2e tests
# Onebox (default) — e2e tests are auto-excluded
uv run pytest tests
# E2E — requires real endpoint + AWS credentials
ETK_API_ENDPOINT=https://... ETK_AWS_REGION=eu-west-2 uv run pytest tests -m e2emise.local.toml example
[env]
ETK_API_ENDPOINT = "https://abc123.execute-api.eu-west-2.amazonaws.com/prod"
ETK_AWS_REGION = "eu-west-2"Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

