Module `aiolirest.models.packaged_model`

HPE Machine Learning Inference Software (MLIS/Aioli)

HPE MLIS is Aioli – The AI On-line Inference Platform that enables easy deployment, tracking, and serving of your packaged models regardless of your preferred AI framework.

The version of the OpenAPI document: 1.0.0 Contact: community@determined-ai Generated by OpenAPI Generator (https://openapi-generator.tech)

Do not edit the class manually.

Expand source code

# coding: utf-8

"""
    HPE Machine Learning Inference Software (MLIS/Aioli)

    HPE MLIS is *Aioli* -- The AI On-line Inference Platform that enables easy deployment, tracking, and serving of your packaged models regardless of your preferred AI framework.

    The version of the OpenAPI document: 1.0.0
    Contact: community@determined-ai
    Generated by OpenAPI Generator (https://openapi-generator.tech)

    Do not edit the class manually.
"""  # noqa: E501


from __future__ import annotations
import pprint
import re  # noqa: F401
import json


from typing import Any, ClassVar, Dict, List, Optional
from pydantic import BaseModel, StrictInt, StrictStr
from pydantic import Field
from aiolirest.models.configuration_resources import ConfigurationResources
try:
    from typing import Self
except ImportError:
    from typing_extensions import Self

class PackagedModel(BaseModel):
    """
    The PackagedModel describes a specific model that can be loaded. It optionally references a model registry to provide authorization, and other details.
    """ # noqa: E501
    arguments: Optional[List[StrictStr]] = Field(default=None, description="Arguments to be added to the service command line")
    description: Optional[StrictStr] = Field(default=None, description="A description of the model.")
    environment: Optional[Dict[str, StrictStr]] = Field(default=None, description="Environment variables added to the service")
    id: Optional[StrictStr] = Field(default=None, description="The ID of the model.  This is a read-only field and is automatically assigned on creation.")
    image: Optional[StrictStr] = Field(default=None, description="Docker container image servicing the model.")
    format: Optional[StrictStr] = Field(default='custom', description="Model format for downloaded models (e.g. from s3, http, etc.). Must be one of the values: (bento-archive, openllm, nim, custom). * `custom` - The packaged model is provided in a container image. * `bento-archive` - The packaged model is a bento archive file (.bento).  It will be downloaded,  expanded, and then  will be served using the `bentolm serve` command in a provided bentoml serving container. * `openllm` - The packaged model will be served using the `openllm serve` command in a  provided openllm serving container. * `nim` - The packaged model will be served using the specified NVIDIA NIM microservices container image.", alias="modelFormat")
    modified_at: Optional[StrictStr] = Field(default=None, description="Date-time of last modification of the model. This is a read-only field and is automatically updated.", alias="modifiedAt")
    name: StrictStr = Field(description="The name of the model.  Must begin with a letter, but may contain letters, numbers, and hyphen.")
    registry: Optional[StrictStr] = Field(default=None, description="The name or ID of the model registry.")
    resources: Optional[ConfigurationResources] = None
    url: Optional[StrictStr] = Field(default=None, description="Reference to the bento or model to be served.  Supported schemes are: * `openllm://` - An openllm model name from huggingface.co dynamically loaded and executed with a VLLM backend. * `s3://` - An openllm model path which will be dynamically downloaded from an associated s3  registry bucket and executed with a VLLM backend. * `ngc://` - An NVIDIA NGC model will be dynamically downloaded from the associated `ngc`  registry bucket and executed with the specified NVIDIA NIM microservices container image.")
    version: Optional[StrictInt] = Field(default=None, description="The version of the model.  This is a read-only field and is automatically assigned on creation.")
    __properties: ClassVar[List[str]] = ["arguments", "description", "environment", "id", "image", "modelFormat", "modifiedAt", "name", "registry", "resources", "url", "version"]

    model_config = {
        "populate_by_name": True,
        "validate_assignment": True
    }


    def to_str(self) -> str:
        """Returns the string representation of the model using alias"""
        return pprint.pformat(self.model_dump(by_alias=True))

    def to_json(self) -> str:
        """Returns the JSON representation of the model using alias"""
        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
        return json.dumps(self.to_dict())

    @classmethod
    def from_json(cls, json_str: str) -> Self:
        """Create an instance of PackagedModel from a JSON string"""
        return cls.from_dict(json.loads(json_str))

    def to_dict(self) -> Dict[str, Any]:
        """Return the dictionary representation of the model using alias.

        This has the following differences from calling pydantic's
        `self.model_dump(by_alias=True)`:

        * `None` is only added to the output dict for nullable fields that
          were set at model initialization. Other fields with value `None`
          are ignored.
        """
        _dict = self.model_dump(
            by_alias=True,
            exclude={
            },
            exclude_none=True,
        )
        # override the default output from pydantic by calling `to_dict()` of resources
        if self.resources:
            _dict['resources'] = self.resources.to_dict()
        return _dict

    @classmethod
    def from_dict(cls, obj: Dict) -> Self:
        """Create an instance of PackagedModel from a dict"""
        if obj is None:
            return None

        if not isinstance(obj, dict):
            return cls.model_validate(obj)

        _obj = cls.model_validate({
            "arguments": obj.get("arguments"),
            "description": obj.get("description"),
            "environment": obj.get("environment"),
            "id": obj.get("id"),
            "image": obj.get("image"),
            "modelFormat": obj.get("modelFormat") if obj.get("modelFormat") is not None else 'custom',
            "modifiedAt": obj.get("modifiedAt"),
            "name": obj.get("name"),
            "registry": obj.get("registry"),
            "resources": ConfigurationResources.from_dict(obj.get("resources")) if obj.get("resources") is not None else None,
            "url": obj.get("url"),
            "version": obj.get("version")
        })
        return _obj

Classes

class PackagedModel (**data: Any)

The PackagedModel describes a specific model that can be loaded. It optionally references a model registry to provide authorization, and other details.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Expand source code

class PackagedModel(BaseModel):
    """
    The PackagedModel describes a specific model that can be loaded. It optionally references a model registry to provide authorization, and other details.
    """ # noqa: E501
    arguments: Optional[List[StrictStr]] = Field(default=None, description="Arguments to be added to the service command line")
    description: Optional[StrictStr] = Field(default=None, description="A description of the model.")
    environment: Optional[Dict[str, StrictStr]] = Field(default=None, description="Environment variables added to the service")
    id: Optional[StrictStr] = Field(default=None, description="The ID of the model.  This is a read-only field and is automatically assigned on creation.")
    image: Optional[StrictStr] = Field(default=None, description="Docker container image servicing the model.")
    format: Optional[StrictStr] = Field(default='custom', description="Model format for downloaded models (e.g. from s3, http, etc.). Must be one of the values: (bento-archive, openllm, nim, custom). * `custom` - The packaged model is provided in a container image. * `bento-archive` - The packaged model is a bento archive file (.bento).  It will be downloaded,  expanded, and then  will be served using the `bentolm serve` command in a provided bentoml serving container. * `openllm` - The packaged model will be served using the `openllm serve` command in a  provided openllm serving container. * `nim` - The packaged model will be served using the specified NVIDIA NIM microservices container image.", alias="modelFormat")
    modified_at: Optional[StrictStr] = Field(default=None, description="Date-time of last modification of the model. This is a read-only field and is automatically updated.", alias="modifiedAt")
    name: StrictStr = Field(description="The name of the model.  Must begin with a letter, but may contain letters, numbers, and hyphen.")
    registry: Optional[StrictStr] = Field(default=None, description="The name or ID of the model registry.")
    resources: Optional[ConfigurationResources] = None
    url: Optional[StrictStr] = Field(default=None, description="Reference to the bento or model to be served.  Supported schemes are: * `openllm://` - An openllm model name from huggingface.co dynamically loaded and executed with a VLLM backend. * `s3://` - An openllm model path which will be dynamically downloaded from an associated s3  registry bucket and executed with a VLLM backend. * `ngc://` - An NVIDIA NGC model will be dynamically downloaded from the associated `ngc`  registry bucket and executed with the specified NVIDIA NIM microservices container image.")
    version: Optional[StrictInt] = Field(default=None, description="The version of the model.  This is a read-only field and is automatically assigned on creation.")
    __properties: ClassVar[List[str]] = ["arguments", "description", "environment", "id", "image", "modelFormat", "modifiedAt", "name", "registry", "resources", "url", "version"]

    model_config = {
        "populate_by_name": True,
        "validate_assignment": True
    }


    def to_str(self) -> str:
        """Returns the string representation of the model using alias"""
        return pprint.pformat(self.model_dump(by_alias=True))

    def to_json(self) -> str:
        """Returns the JSON representation of the model using alias"""
        # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
        return json.dumps(self.to_dict())

    @classmethod
    def from_json(cls, json_str: str) -> Self:
        """Create an instance of PackagedModel from a JSON string"""
        return cls.from_dict(json.loads(json_str))

    def to_dict(self) -> Dict[str, Any]:
        """Return the dictionary representation of the model using alias.

        This has the following differences from calling pydantic's
        `self.model_dump(by_alias=True)`:

        * `None` is only added to the output dict for nullable fields that
          were set at model initialization. Other fields with value `None`
          are ignored.
        """
        _dict = self.model_dump(
            by_alias=True,
            exclude={
            },
            exclude_none=True,
        )
        # override the default output from pydantic by calling `to_dict()` of resources
        if self.resources:
            _dict['resources'] = self.resources.to_dict()
        return _dict

    @classmethod
    def from_dict(cls, obj: Dict) -> Self:
        """Create an instance of PackagedModel from a dict"""
        if obj is None:
            return None

        if not isinstance(obj, dict):
            return cls.model_validate(obj)

        _obj = cls.model_validate({
            "arguments": obj.get("arguments"),
            "description": obj.get("description"),
            "environment": obj.get("environment"),
            "id": obj.get("id"),
            "image": obj.get("image"),
            "modelFormat": obj.get("modelFormat") if obj.get("modelFormat") is not None else 'custom',
            "modifiedAt": obj.get("modifiedAt"),
            "name": obj.get("name"),
            "registry": obj.get("registry"),
            "resources": ConfigurationResources.from_dict(obj.get("resources")) if obj.get("resources") is not None else None,
            "url": obj.get("url"),
            "version": obj.get("version")
        })
        return _obj

Ancestors

pydantic.main.BaseModel

Class variables

var arguments : Optional[List[str]]
var description : Optional[str]
var environment : Optional[Dict[str, str]]
var format : Optional[str]
var id : Optional[str]
var image : Optional[str]
var model_computed_fields
var model_config
var model_fields
var modified_at : Optional[str]
var name : str
var registry : Optional[str]
var resources : Optional[ConfigurationResources]
var url : Optional[str]
var version : Optional[int]

Static methods

def from_dict(obj: Dict) ‑> Self

Create an instance of PackagedModel from a dict

Expand source code

@classmethod
def from_dict(cls, obj: Dict) -> Self:
    """Create an instance of PackagedModel from a dict"""
    if obj is None:
        return None

    if not isinstance(obj, dict):
        return cls.model_validate(obj)

    _obj = cls.model_validate({
        "arguments": obj.get("arguments"),
        "description": obj.get("description"),
        "environment": obj.get("environment"),
        "id": obj.get("id"),
        "image": obj.get("image"),
        "modelFormat": obj.get("modelFormat") if obj.get("modelFormat") is not None else 'custom',
        "modifiedAt": obj.get("modifiedAt"),
        "name": obj.get("name"),
        "registry": obj.get("registry"),
        "resources": ConfigurationResources.from_dict(obj.get("resources")) if obj.get("resources") is not None else None,
        "url": obj.get("url"),
        "version": obj.get("version")
    })
    return _obj

def from_json(json_str: str) ‑> Self

Create an instance of PackagedModel from a JSON string

Expand source code

@classmethod
def from_json(cls, json_str: str) -> Self:
    """Create an instance of PackagedModel from a JSON string"""
    return cls.from_dict(json.loads(json_str))

Methods

def model_post_init(self: BaseModel, context: Any, /) ‑> None

This function is meant to behave like a BaseModel method to initialise private attributes.

It takes context as an argument since that's what pydantic-core passes when calling it.

Args

self: The BaseModel instance.
context: The context.

Expand source code

def init_private_attributes(self: BaseModel, context: Any, /) -> None:
    """This function is meant to behave like a BaseModel method to initialise private attributes.

    It takes context as an argument since that's what pydantic-core passes when calling it.

    Args:
        self: The BaseModel instance.
        context: The context.
    """
    if getattr(self, '__pydantic_private__', None) is None:
        pydantic_private = {}
        for name, private_attr in self.__private_attributes__.items():
            default = private_attr.get_default()
            if default is not PydanticUndefined:
                pydantic_private[name] = default
        object_setattr(self, '__pydantic_private__', pydantic_private)

def to_dict(self) ‑> Dict[str, Any]

Return the dictionary representation of the model using alias.

This has the following differences from calling pydantic's self.model_dump(by_alias=True):

None is only added to the output dict for nullable fields that were set at model initialization. Other fields with value None are ignored.

Expand source code

def to_dict(self) -> Dict[str, Any]:
    """Return the dictionary representation of the model using alias.

    This has the following differences from calling pydantic's
    `self.model_dump(by_alias=True)`:

    * `None` is only added to the output dict for nullable fields that
      were set at model initialization. Other fields with value `None`
      are ignored.
    """
    _dict = self.model_dump(
        by_alias=True,
        exclude={
        },
        exclude_none=True,
    )
    # override the default output from pydantic by calling `to_dict()` of resources
    if self.resources:
        _dict['resources'] = self.resources.to_dict()
    return _dict

def to_json(self) ‑> str

Returns the JSON representation of the model using alias

Expand source code

def to_json(self) -> str:
    """Returns the JSON representation of the model using alias"""
    # TODO: pydantic v2: use .model_dump_json(by_alias=True, exclude_unset=True) instead
    return json.dumps(self.to_dict())

def to_str(self) ‑> str

Returns the string representation of the model using alias

Expand source code

def to_str(self) -> str:
    """Returns the string representation of the model using alias"""
    return pprint.pformat(self.model_dump(by_alias=True))