agentleFS
AWSKnown publisherawslabs/gen-ai-evaluation-toolkit-on-aws/packages/python-api/CLAUDE.md

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).

The file

Files
CLAUDE.md

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 models

Commands

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 check

Key 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 e2e

mise.local.toml example

[env]
ETK_API_ENDPOINT = "https://abc123.execute-api.eu-west-2.amazonaws.com/prod"
ETK_AWS_REGION = "eu-west-2"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.