from app.models.models import ClassificationModel, MLModel, InferenceResult from app.inference.mbert import MBert from app.inference.mlp import MLP from app.inference.bilistm import BiLstm from app.inference.ml import MachineLearning from app.core.context import request_id_ctx import logging import time logger = logging.getLogger(__name__) class InferenceService: def __init__(self): self.models: dict[ ClassificationModel, MBert | MLP | BiLstm | MachineLearning ] = { ClassificationModel.bert: MBert(), ClassificationModel.bilstm: BiLstm(), ClassificationModel.mlp: MLP(), ClassificationModel.naivebayes: MachineLearning(model=MLModel.naivebayes), ClassificationModel.gradientboost: MachineLearning(model=MLModel.gradientboost), ClassificationModel.xgboost: MachineLearning(model=MLModel.xgboost), } def run_inference( self, model: ClassificationModel, text: str, ) -> str: request_id = request_id_ctx.get('not-set') logger.info( "starting_inference_run", extra={ "request_id": request_id, "model": model, "text_length": len(text.split()), } ) start_time = time.perf_counter() instance = self.models.get(model) if instance is None: logger.error( "inference_model_not_found", extra={ "request_id": request_id, "model": model, } ) raise ValueError( f"Unknown model: {model}" ) try: prediction: str = instance.predict(text=text) logger.info( "inference_completed_successfully", extra={ "request_id": request_id, "model": model, "duration": round((time.perf_counter() - start_time) * 1000), "words_processed": min(instance.MAX_SEQUENCE_LENGTH, len(text.split())) } ) return InferenceResult( prediction = prediction ) except Exception as e: logger.info( "inference_failed", extra={ "request_id": request_id, "model": model, "duration": round((time.perf_counter() - start_time) * 1000), "error": str(e), } ) raise e inference_service = InferenceService()