[BUG] Better alignment with REST API: send 500 not 400 if predictor couldn't get loaded

Describe the bug
Hi! first of all, thanks for such a neat tool! 🎉

It's not a bug, I just thought that sending HTTP 400 is not good when the predictor couldn't get loaded (all /predict* routes):

budgetml/server/app/main.py

Lines 96 to 105 in 7ade99c

    
           @app.post("/predict/") 
        
           async def predict(request: Request, 
        
                             _: str = Depends(verify)) -> Response: 
        
               global PREDICTOR 
        
               if PREDICTOR is None: 
        
                   raise HTTPException( 
        
                       status_code=400, 
        
                       detail="The predictor could not be loaded. Please check the logs " 
        
                              "for more detail.", 
        
                   )

I think, it's better to use a 5XX server-side error:

HTTP 400 means that there was a client error (e.g., malformed request syntax, invalid request message framing, or deceptive request routing).
HTTP 500 means that the server encountered an unexpected condition that prevented it from fulfilling the request. This error response is a generic "catch-all" response. Usually, this indicates the server cannot find a better 5xx error code to response.

Good catch! I pushed it now with this commit.. Also directly updated the base image so that it gets reflected on future runs (Not the most professional but I did not want to wait for the next release of BudgetML to accommodate this small request 👍 )

	@app.post("/predict/")
	async def predict(request: Request,
	_: str = Depends(verify)) -> Response:
	global PREDICTOR
	if PREDICTOR is None:
	raise HTTPException(
	status_code=400,
	detail="The predictor could not be loaded. Please check the logs "
	"for more detail.",
	)