Develop and Deploy a Machine Learning Model

class MyModel(object):
    """
    Model template. You can load your model parameters in __init__ from a
    location accessible at runtime
    """

    def __init__(self):
        """
        Add any initialization parameters. These will be passed at runtime
        from the graph definition parameters defined in your seldondeployment
        kubernetes resource manifest.
        """
        print("Initializing")

    def predict(self,X,features_names,**kwargs):
        """
        Return a prediction.

        Parameters
        ----------
        X : array-like
        feature_names : array of feature names (optional)
        """
        print("Predict called - will run identity function")
        return X

    def  class_names(self):
        return ["X_name"]

import logging
import os

from transformers import AutoTokenizer, AutoModel
from torch.nn import functional as F
from typing import Iterable
import numpy as np
import torch

log = logging.getLogger()

class mini():
    def __init__(self):
        self.tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
        self.model= AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')

    #Mean Pooling
    def mean_pooling(self, model_output, attention_mask):
        token_embeddings = model_output[0] #First element of model_output contains all token embeddings
        input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
        return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)

    def predict(self, X:np.ndarray, names=None, **kwargs):
        #   In Fusion there are several variables passed in the numpy array with the Milvus Query stage,
        #   Encode to Milvus index stage, and Vectorize Seldon index and query stage:
        #   [pipeline, bool, and text]. Text is what variable will be encoded, so that is what will be set to 'text'
        #   When using the Machine Learning stage, the input map keys should match what what is in this file.

        model_input = dict(zip(names, X))
        text = model_input["text"]

        with torch.inference_mode(): # Allows torch to run more quickly
          # Tokenize sentences
          encoded_input = self.tokenizer(text, padding=True, truncation=True, return_tensors='pt')
          log.debug('encoded input',str(encoded_input))
          model_output = self.model(**encoded_input)
          log.debug('model output',str(model_output))

          # Perform pooling. In this case, max pooling.
          sentence_embeddings = self.mean_pooling(model_output, encoded_input['attention_mask'])
          # Normalize embeddings, because Fusion likes it that way.
          sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=-1)
          # Fixing the shape of the emebbedings to match (1, 384).
          final = [sentence_embeddings.squeeze().cpu().detach().numpy().tolist()]
        return final

    def class_names(self) -> Iterable[str]:
        return ["vector"]

#It is important that python version is 3.x-slim for seldon-core
FROM python:3.9-slim
# Whatever directory(folder)the python file for your python class, Dockerfile, and
# requirements.txt is in should be copied then denoted as the work directory.
COPY . /app
WORKDIR /app

# The requirements file for the Docker container
COPY requirements.txt requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Copy source code
COPY . .

# GRPC - Allows Fusion to do a Remote Procedure Call
EXPOSE 5000

# Define environment variable for seldon-core
# !!!MODEL_NAME must be the EXACT same as the python file & python class name!!!
ENV MODEL_NAME mini
ENV SERVICE_TYPE MODEL
ENV PERSISTENCE 0

# Changing active directory folder (same one as above on lines 5 & 6) to default user, required for Fusion
RUN chown -R 8888 /app

# Command to wrap python class with seldon-core to allow it to be usable in Fusion
CMD ["sh", "-c", "seldon-core-microservice $MODEL_NAME --service-type $SERVICE_TYPE --persistence $PERSISTENCE"]

# You can use the following if You need shell features like environment variable expansion or
# You need to use shell constructs like pipes, redirects, etc.
# See https://docs.docker.com/reference/dockerfile/#cmd for more details.
# CMD exec seldon-core-microservice $MODEL_NAME --service-type $SERVICE_TYPE --persistence $PERSISTENCE

seldon-core
torch
transformers
numpy

pip freeze > requirements.txt

DOCKER_DEFAULT_PLATFORM=linux/amd64 docker build . -t [DOCKERHUB-USERNAME]/[REPOSITORY]:[VERSION-TAG]

docker push [DOCKERHUB USERNAME]/[REPOSITORY]:[VERSION-TAG]

DOCKER_DEFAULT_PLATFORM=linux/amd64 docker build . -t jstrmec/example_sbert_model:0.14; docker push jstrmec/example_sbert_model:0.14