sentirisk/api.py

from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
import os
import sys

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.append(BASE_DIR)

from model import SentiRiskEngine

app = FastAPI(
    title="SentiRisk SML API",
    description="Independent Small Machine Learning (SML) service for institutional risk assessment.",
    version="1.0.0"
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)

WEIGHTS_PATH = os.path.join(BASE_DIR, "weights", "risk_model.pt")
engine = SentiRiskEngine(WEIGHTS_PATH)

class RequestBody(BaseModel):
    text: str

@app.get("/")
async def root():
    return {"status": "active", "service": "SentiRisk", "port": 9205}

@app.get("/health")
async def health():
    return {"status": "ok"}

@app.post("/api/v1/risk/score")
async def risk_score(body: RequestBody):
    try:
        return engine.predict(body.text)
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

@app.post("/api/v1/risk/assess")
async def risk_assess(body: RequestBody):
    try:
        return engine.predict(body.text)
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))


@app.post("/api/v1/risk/predict")
async def predict_endpoint_legacy_alias(body: RequestBody):
    try:
        # Try different possible engines
        if 'engine' in globals():
            return engine.predict(body.text)
        elif 'rlm_engine' in globals():
            return await rlm_engine.predict_deep(body.text, "A")
        else:
            return {"status": "ok", "service": "sentirisk"}
    except Exception as e:
        raise HTTPException(status_code=500, detail=str(e))

if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=9205)