MLflow

specification: "0.3"
type: "file"
source: "Custom Model"
version: "0.0.1"
name: "Sample Model Name"
author: "Sample Model Author"
description:
  summary: "Short description of model."
  details: "Longer description of what the model does, what inputs it expects, and what outputs it returns."
  technical: |-
    #OVERVIEW:
    A continuation of "details" section that may include any information about model architecture, use cases, and any other general information.
    #TRAINING:
    Training-specific information, including links to the training dataset, a list of specific training techniques used, and any other development-specific information.
    #VALIDATION:
    Information about how the model was validated and any relevant dataset-specific information.
    #INPUT SPECIFICATION:
    Detailed description of expected inputs the model expects.
    #OUTPUT DETAILS:
    Detailed description of the output the model returns.
  performance: "Description about the model's performance on validation dataset. Include common machine learning evaluation metrics."
releaseNotes: "Short phrase describing new model version."

tags:[]
filters:
- type: "Task"
  label: "<task>"
- type: "Input Type"
  label: "<input data type>"
- type: "Subject"
  label: "<subject>"

metrics:
- label: "Probability"
  type: "percentage"
  value: 1.0
  description: |-
    Use case dependent
inputs:
  image:
    acceptedMediaTypes:
      - "image/jpeg"
      - "image/png"
      - "image/tiff"
    maxSize: 5M
    description: "Any jpg or png image for object detection"

outputs:
  results.json:
    mediaType: "application/json"
    maxSize: 128K
    description: "Classify objects in an image and give probabilities for each"

# replace size, cpu-count, and gpu-count values to reflect the resources your model needs to run
resources:
  memory:
    size: 6G
  cpu:
    count: 1
  gpu:
    count: 1

timeout:
  status: 20s # amount of time it will take your model to load and spin up
  run: 20s # amount of time it will take your model to complete inference 

# keep these values as are
internal:
  recommended: false
  experimental: false
  available: true
  active: true
  features:
    explainable: false
    adversarialDefense: false

import os
import json
import time

os.environ["MODZY_API_KEY"] = "modzy-api-key"
os.environ["SP_ACCESS_KEY"] = "cloud-storage-access-key"
os.environ["SP_SECRET_ACCESS_KEY"] = "cloud-storage-secret-key"

from modzy.converter.model_converter import ModelConverter
from modzy.client import ApiClient

# Create a Modzy API client to interact with your Modzy envrionment
modzy_api_key = os.getenv("MODZY_API_KEY")
modzy_instance_base_url = "https://<your-modzy-instance-url>/api"
modzy_api_client = ApiClient(api_key=modzy_api_key, base_url=modzy_instance_base_url)

# Instantiate a Model Converter client with access to your Modzy environment
model_converter = ModelConverter(modzy_api_client)

blob_storage_provider = "S3"
blob_storage_container = "<path-to-your-s3-bucket>"

from modzy.converter.utils import upload_resources

current_working_directory = os.getcwd()

# Define source platform and model type
source_platform = "mlflow"
model_type = "tabular"

# Paths to your local files
model_weights_path = os.path.join(current_working_directory, "local-file-path/weights.pt") # TODO check this type of file
model_yaml_path = os.path.join(current_working_directory, "local-file-path/model.yaml")

# Your local files will be archieved and stored in the following location:
weights_key = "cloud-storage-path-to-weights/weights.tar.gz"
resources_key = "cloud-storage-path-to-resources/resources.tar.gz"

# Utility function to wrap resources in tar archive and upload to specified cloud storage filepath
upload_resources(
    model_yaml_path, blob_storage_container, resources_key,
    os.getenv("SP_ACCESS_KEY_ID"), os.getenv("SP_SECRET_ACCESS_KEY"), blob_storage_provider
)

# Utility function to wrap model weights in tar archive and upload to specified cloud storage filepath
upload_model_dir(
    model_weights_path, blob_storage_container, weights_key,
    os.getenv("SP_ACCESS_KEY_ID"), os.getenv("SP_SECRET_ACCESS_KEY"), blob_storage_provider, "mlflow"
)

# Now, provide the Model converter with information about your stored model assets and the credentials required
# to access them. The Model converter will do the rest of the work.

converter_output = model_converter.start(
    sp_access_key_id=os.getenv("SP_ACCESS_KEY_ID"),
    sp_secret_access_key=os.getenv("SP_SECRET_ACCESS_KEY"),
    blobstore_provider=blob_storage_provider,
    blobstore_container=blob_storage_container,
    weights_path=weights_key,
    resources_path=resources_key,
    platform=source_platform,
    model_type=model_type,
)

job_id = converter_output["jobId"]

print("Model Converter Status: {} - {}".format(converter_output["status"], converter_output["message"]) + '\n' + "Model Converter Job ID: {}".format(job_id))

# Block Model Converter Job until complete
start_time = time.time()
converter_result = model_converter.block_until_complete(job_id, timeout=600)
end_time = time.time()
model_id = converter_result["modelId"]
model_version = converter_result["modelVersion"]
print("Model Converter Job Status: {}".format(converter_result["message"]) + '\n' + "Completed in {} minutes".format((end_time - start_time)/60) + '\n' + "Find your newly deployed model here: {}/models/{}/{}".format(modzy_instance_base_url[:-4], model_id, model_version))