Release prep: ensemble-aware CLI/server, clean-install validation, compact Run locally section and local inference doc
5f15b97 verified | """Jev-compatible HTTP server for Pluto.""" | |
| from __future__ import annotations | |
| import os | |
| from typing import Any | |
| from fastapi import FastAPI, Header, HTTPException | |
| from pydantic import BaseModel, Field | |
| from .loader import load_engine | |
| from .schema import SchemaError | |
| class DecisionRequest(BaseModel): | |
| state: Any | |
| questions: dict[str, Any] | |
| max_len: int | None = None | |
| class Health(BaseModel): | |
| status: str | |
| model: str | |
| params: int | |
| device: str | |
| def create_app(model_path: str | None = None, device: str | None = None) -> FastAPI: | |
| path = model_path or os.environ.get("PLUTO_MODEL", "omida-ai/pluto-1") | |
| engine = load_engine(path, device=device or os.environ.get("PLUTO_DEVICE")) | |
| api_key = os.environ.get("PLUTO_API_KEY") | |
| app = FastAPI(title="Pluto Decision API", version="0.1.0") | |
| def health() -> Health: | |
| info = engine.info | |
| return Health(status="ok", model=info["name"], params=info["params"], device=info["device"]) | |
| def models() -> dict: | |
| return {"data": [{"id": engine.model_name, "object": "model", "owned_by": "omida"}]} | |
| def systemone(req: DecisionRequest, authorization: str | None = Header(default=None)) -> dict: | |
| if api_key: | |
| expected = f"Bearer {api_key}" | |
| if authorization != expected: | |
| raise HTTPException(status_code=401, detail="invalid API key") | |
| try: | |
| return engine.predict(req.state, req.questions, max_len=req.max_len) | |
| except SchemaError as e: | |
| raise HTTPException(status_code=422, detail=str(e)) from e | |
| except ValueError as e: | |
| raise HTTPException(status_code=422, detail=str(e)) from e | |
| return app | |
| app = None | |