Launchpad

Launchpad provides a standardized way to turn AI/ML research implementations into reusable, production-ready capabilities. Define your capability once with typed Pydantic contracts — Launchpad handles how it gets delivered.

Why Launchpad?

AI teams repeatedly solve the same problems: wrapping a model call in retry logic, exposing a capability as an API, logging inputs/outputs for evaluation, versioning prompts. Launchpad makes this a one-time effort.

You implement a capability once. Launchpad handles:

• Multiple delivery mechanisms — REST API, gRPC, CLI, SDK import, async queue
• Typed contracts — Pydantic models as first-class input/output schemas, validated at every boundary
• Observability — structured logging, tracing, evaluation hooks
• Configuration — prompt versioning, model routing, runtime overrides
• Reliability — retries, fallbacks, circuit breakers

Core Concepts

Quick Start

pip install launchpad-ai
pip install 'launchpad-ai[http]'  # for the HTTP adapter

Define your contracts as Pydantic models, then implement the capability:

from pydantic import BaseModel
from launchpad import Capability, capability

class SummarizeInput(BaseModel):
    text: str
    max_length: int = 200

class SummarizeOutput(BaseModel):
    summary: str

@capability(name="summarize", version="1.0")
class Summarize(Capability[SummarizeInput, SummarizeOutput]):
    def run(self, input: SummarizeInput) -> SummarizeOutput:
        # your implementation here
        ...

Use it directly:

result = Summarize().run(SummarizeInput(text="..."))
print(result.summary)

Or serve it over HTTP:

from launchpad.adapters.http import HttpAdapter

HttpAdapter(Summarize).serve(port=8080)
# POST /summarize  →  { "text": "...", "max_length": 200 }
# GET  /health
# GET  /docs       (OpenAPI)

Project Structure

launchpad/
├── src/launchpad/
│   ├── core/          # Capability[I,O] base class and @capability decorator
│   ├── adapters/      # http/ — delivery mechanisms
│   ├── pipeline/      # Capability composition
│   ├── observability/ # Structured logging, OpenTelemetry, eval hooks
│   └── config/        # Prompt versioning, model routing
├── examples/          # Self-contained runnable examples
└── tests/

Documentation

See AGENTS.md for conventions used when building capabilities and adapters in this repo.

License

Apache 2.0