Generate a new SparkGen-AWS project from the cookiecutter template
Generate a new project from the SparkGen-AWS cookiecutter template.
Before generating:
cookiecutter.json to understand all available template variablescookiecutter --versionMap the user's arguments to cookiecutter variables:
| Argument | cookiecutter Variable | Default |
|---|---|---|
| project_name | project_name | "My SparkGen AWS Agent" |
| --mode | deployment_mode | "all" |
| --agents | num_agents | "4" |
| --rag | enable_rag |
| "yes" |
| --provider | llm_provider | "bedrock" |
Build the cookiecutter command with --no-input and variable overrides:
cookiecutter . --no-input \
project_name="<name>" \
deployment_mode="<mode>" \
num_agents="<N>" \
enable_rag="<yes|no>" \
llm_provider="<provider>"
After generating:
ls <output_slug>/python -m compileall <output_slug>/app -q<output_slug>/config/ai_workflow.yaml<output_slug>/Makefile<output_slug>/app/api.py<output_slug>/.claude/skills/ (skills directory)<output_slug>/CLAUDE.mdgrep "^ - name:" <output_slug>/config/ai_workflow.yaml=== Project Generated ===
Name: <project_name>
Location: ./<output_slug>/
Mode: <deployment_mode>
Provider: <llm_provider>
Agents: <num_agents>
RAG: <enable_rag>
Guardrails: <enable_guardrails>
Next steps:
cd <output_slug>
make setup # Install dependencies
make local # Start local dev server
Available skills (in generated project):
/sparkgen-deploy Deploy to local/docker/aws
/sparkgen-test Run tests
/sparkgen-chat Test chat
/sparkgen-debug Diagnose issues
pip install cookiecutter