oracle-ads 2.13.9rc0__py3-none-any.whl → 2.13.10__py3-none-any.whl

ads/aqua/config/utils/serializer.py

@@ -0,0 +1,339 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2024 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+import json
+from typing import Union
+from urllib.parse import urlparse
+
+import fsspec
+import yaml
+from pydantic import BaseModel
+from yaml import SafeLoader as Loader
+
+from ads.common.auth import default_signer
+
+
+class Serializable(BaseModel):
+    """Base class that represents a serializable item.
+
+    Methods
+    -------
+    to_json(self, uri=None, **kwargs)
+        Returns object serialized as a JSON string
+    from_json(cls, json_string=None, uri=None, **kwargs)
+        Creates an object from JSON string provided or from URI location containing JSON string
+    to_yaml(self, uri=None, **kwargs)
+        Returns object serialized as a YAML string
+    from_yaml(cls, yaml_string=None, uri=None, **kwargs)
+        Creates an object from YAML string provided or from URI location containing YAML string
+    """
+
+    @staticmethod
+    def _write_to_file(s: str, uri: str, **kwargs) -> None:
+        """Write string s into location specified by uri.
+
+        Parameters
+        ----------
+        s: (string)
+            content
+        uri: (string)
+            URI location to save string s
+        kwargs : dict
+            keyword arguments to be passed into fsspec.open().
+            For OCI object storage, this can be config="path/to/.oci/config".
+
+        Returns
+        -------
+        None
+            Nothing
+        """
+
+        overwrite = kwargs.pop("overwrite", True)
+        if not overwrite:
+            dst_path_scheme = urlparse(uri).scheme or "file"
+            if fsspec.filesystem(dst_path_scheme, **kwargs).exists(uri):
+                raise FileExistsError(
+                    f"The `{uri}` is already exists. Set `overwrite` to True "
+                    "if you wish to overwrite."
+                )
+
+        with fsspec.open(uri, "w", **kwargs) as f:
+            f.write(s)
+
+    @staticmethod
+    def _read_from_file(uri: str, **kwargs) -> str:
+        """Returns contents from location specified by URI
+
+        Parameters
+        ----------
+        uri: (string)
+            URI location
+        kwargs : dict
+            keyword arguments to be passed into fsspec.open().
+            For OCI object storage, this can be config="path/to/.oci/config".
+
+        Returns
+        -------
+        string: Contents in file specified by URI
+        """
+        # Add default signer if the uri is an object storage uri, and
+        # the user does not specify config or signer.
+        if (
+            uri.startswith("oci://")
+            and "config" not in kwargs
+            and "signer" not in kwargs
+        ):
+            kwargs.update(default_signer())
+        with fsspec.open(uri, "r", **kwargs) as f:
+            return f.read()
+
+    def to_json(
+        self,
+        uri: str = None,
+        encoder: callable = json.JSONEncoder,
+        default: callable = None,
+        **kwargs,
+    ) -> str:
+        """Returns object serialized as a JSON string
+
+        Parameters
+        ----------
+        uri: (string, optional)
+            URI location to save the JSON string. Defaults to None.
+        encoder: (callable, optional)
+            Encoder for custom data structures. Defaults to JSONEncoder.
+        default: (callable, optional)
+            A function that gets called for objects that can't otherwise be serialized.
+            It should return JSON-serializable version of the object or original object.
+
+        kwargs
+        ------
+        overwrite: (bool, optional). Defaults to True.
+            Whether to overwrite existing file or not.
+
+        keyword arguments to be passed into fsspec.open().
+        For OCI object storage, this could be config="path/to/.oci/config".
+        For other storage connections consider e.g. host, port, username, password, etc.
+
+        Returns
+        -------
+        Union[str, None]
+            Serialized version of object.
+            `None` in case when `uri` provided.
+        """
+        json_string = json.dumps(
+            self.model_dump(exclude_none=kwargs.pop("exclude_none", False)),
+            cls=encoder,
+            default=default,
+        )
+        if uri:
+            self._write_to_file(s=json_string, uri=uri, **kwargs)
+            return None
+        return json_string
+
+    def to_dict(self) -> dict:
+        """Returns object serialized as a dictionary
+
+        Returns
+        -------
+        dict
+            Serialized version of object
+        """
+        return json.loads(self.to_json())
+
+    @classmethod
+    def from_json(
+        cls,
+        json_string: str = None,
+        uri: str = None,
+        decoder: callable = json.JSONDecoder,
+        **kwargs,
+    ):
+        """Creates an object from JSON string provided or from URI location containing JSON string
+
+        Parameters
+        ----------
+        json_string: (string, optional)
+            JSON string. Defaults to None.
+        uri: (string, optional)
+            URI location of file containing JSON string. Defaults to None.
+        decoder: (callable, optional)
+            Custom decoder. Defaults to simple JSON decoder.
+        kwargs
+        ------
+        keyword arguments to be passed into fsspec.open(). For OCI object storage, this should be config="path/to/.oci/config".
+            For other storage connections consider e.g. host, port, username, password, etc.
+
+        Raises
+        ------
+        ValueError
+            Raised if neither string nor uri is provided
+
+        Returns
+        -------
+        cls
+            Returns instance of the class
+        """
+        if json_string:
+            return cls(**json.loads(json_string, cls=decoder))
+        if uri:
+            return cls(**json.loads(cls._read_from_file(uri, **kwargs), cls=decoder))
+        raise ValueError("Must provide either JSON string or URI location")
+
+    def to_yaml(
+        self, uri: str = None, dumper: callable = yaml.SafeDumper, **kwargs
+    ) -> Union[str, None]:
+        """Returns object serialized as a YAML string
+
+        Parameters
+        ----------
+        uri : str, optional
+            URI location to save the YAML string, by default None
+        dumper : callable, optional
+            Custom YAML Dumper, by default yaml.SafeDumper
+        kwargs : dict
+            overwrite: (bool, optional). Defaults to True.
+                Whether to overwrite existing file or not.
+            note: (str, optional)
+                The note that needs to be added in the beginning of the YAML.
+                It will be added as is without any formatting.
+            side_effect: Optional[SideEffect]
+                side effect to take on the dictionary. The side effect can be either
+                convert the dictionary keys to "lower" (SideEffect.CONVERT_KEYS_TO_LOWER.value)
+                or "upper"(SideEffect.CONVERT_KEYS_TO_UPPER.value) cases.
+
+            The other keyword arguments to be passed into fsspec.open().
+            For OCI object storage, this could be config="path/to/.oci/config".
+
+        Returns
+        -------
+        Union[str, None]
+            Serialized version of object.
+            `None` in case when `uri` provided.
+        """
+        note = kwargs.pop("note", "")
+
+        yaml_string = f"{note}\n" + yaml.dump(
+            self.model_dump(exclude_none=kwargs.pop("exclude_none", False)),
+            Dumper=dumper,
+        )
+        if uri:
+            self._write_to_file(s=yaml_string, uri=uri, **kwargs)
+            return None
+
+        return yaml_string
+
+    @classmethod
+    def from_yaml(
+        cls,
+        yaml_string: str = None,
+        uri: str = None,
+        loader: callable = Loader,
+        **kwargs,
+    ):
+        """Creates an object from YAML string provided or from URI location containing YAML string
+
+        Parameters
+        ----------
+        yaml_string (string, optional)
+            YAML string. Defaults to None.
+        uri (string, optional)
+            URI location of file containing YAML string. Defaults to None.
+        loader (callable, optional)
+            Custom YAML loader. Defaults to CLoader/SafeLoader.
+        kwargs (dict)
+            keyword arguments to be passed into fsspec.open().
+            For OCI object storage, this should be config="path/to/.oci/config".
+            For other storage connections consider e.g. host, port, username, password, etc.
+
+        Raises
+        ------
+        ValueError
+            Raised if neither string nor uri is provided
+
+        Returns
+        -------
+        cls
+            Returns instance of the class
+        """
+        if yaml_string:
+            return cls(**yaml.load(yaml_string, Loader=loader))
+        if uri:
+            return cls(
+                **yaml.load(cls._read_from_file(uri=uri, **kwargs), Loader=loader)
+            )
+        raise ValueError("Must provide either YAML string or URI location")
+
+    @classmethod
+    def schema_to_yaml(cls, uri: str = None, **kwargs) -> Union[str, None]:
+        """Returns the schema serialized as a YAML string
+
+        Parameters
+        ----------
+        uri : str, optional
+            URI location to save the YAML string, by default None
+        dumper : callable, optional
+            Custom YAML Dumper, by default yaml.SafeDumper
+        kwargs : dict
+            overwrite: (bool, optional). Defaults to True.
+                Whether to overwrite existing file or not.
+        Returns
+        -------
+        Union[str, None]
+            Serialized schema.
+            `None` in case when `uri` provided.
+        """
+        yaml_string = yaml.dump(cls.model_json_schema(), sort_keys=False)
+
+        if uri:
+            cls._write_to_file(s=yaml_string, uri=uri, **kwargs)
+            return None
+
+        return yaml_string
+
+    @classmethod
+    def schema_to_json(
+        cls,
+        uri: str = None,
+        encoder: callable = json.JSONEncoder,
+        default: callable = None,
+        **kwargs,
+    ) -> Union[str, None]:
+        """Returns the schema serialized as a JSON string
+
+        Parameters
+        ----------
+        uri: (string, optional)
+            URI location to save the JSON string. Defaults to None.
+        encoder: (callable, optional)
+            Encoder for custom data structures. Defaults to JSONEncoder.
+        default: (callable, optional)
+            A function that gets called for objects that can't otherwise be serialized.
+            It should return JSON-serializable version of the object or original object.
+
+        kwargs
+        ------
+        overwrite: (bool, optional). Defaults to True.
+            Whether to overwrite existing file or not.
+
+        keyword arguments to be passed into fsspec.open().
+        For OCI object storage, this could be config="path/to/.oci/config".
+        For other storage connections consider e.g. host, port, username, password, etc.
+
+        Returns
+        -------
+        Union[str, None]
+            Serialized version of object.
+            `None` in case when `uri` provided.
+        """
+        json_string = json.dumps(
+            cls.model_json_schema(),
+            cls=encoder,
+            default=default,
+        )
+        if uri:
+            cls._write_to_file(s=json_string, uri=uri, **kwargs)
+            return None
+        return json_string

ads/aqua/constants.py

@@ -0,0 +1,116 @@
+#!/usr/bin/env python
+# Copyright (c) 2024, 2025 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+"""This module defines constants used in ads.aqua module."""
+
+UNKNOWN_VALUE = ""
+READY_TO_IMPORT_STATUS = "TRUE"
+UNKNOWN_DICT = {}
+DEPLOYMENT_CONFIG = "deployment_config.json"
+FINE_TUNING_CONFIG = "ft_config.json"
+README = "README.md"
+LICENSE = "LICENSE.txt"
+AQUA_MODEL_TOKENIZER_CONFIG = "tokenizer_config.json"
+COMPARTMENT_MAPPING_KEY = "service-model-compartment"
+CONTAINER_INDEX = "container_index.json"
+EVALUATION_REPORT_JSON = "report.json"
+EVALUATION_REPORT_MD = "report.md"
+EVALUATION_REPORT = "report.html"
+UNKNOWN_JSON_STR = "{}"
+UNKNOWN_JSON_LIST = "[]"
+FINE_TUNING_RUNTIME_CONTAINER = "iad.ocir.io/ociodscdev/aqua_ft_cuda121:0.3.17.20"
+DEFAULT_FT_BLOCK_STORAGE_SIZE = 750
+DEFAULT_FT_REPLICA = 1
+DEFAULT_FT_BATCH_SIZE = 1
+DEFAULT_FT_VALIDATION_SET_SIZE = 0.1
+MAXIMUM_ALLOWED_DATASET_IN_BYTE = 52428800  # 1024 x 1024 x 50 = 50MB
+JOB_INFRASTRUCTURE_TYPE_DEFAULT_NETWORKING = "ME_STANDALONE"
+NB_SESSION_IDENTIFIER = "NB_SESSION_OCID"
+LIFECYCLE_DETAILS_MISSING_JOBRUN = "The associated JobRun resource has been deleted."
+READY_TO_DEPLOY_STATUS = "ACTIVE"
+READY_TO_FINE_TUNE_STATUS = "TRUE"
+PRIVATE_ENDPOINT_TYPE = "MODEL_DEPLOYMENT"
+AQUA_GA_LIST = ["id19sfcrra6z"]
+AQUA_MULTI_MODEL_CONFIG = "MULTI_MODEL_CONFIG"
+AQUA_MODEL_TYPE_SERVICE = "service"
+AQUA_MODEL_TYPE_CUSTOM = "custom"
+AQUA_MODEL_TYPE_MULTI = "multi_model"
+AQUA_MODEL_ARTIFACT_CONFIG = "config.json"
+AQUA_MODEL_ARTIFACT_CONFIG_MODEL_NAME = "_name_or_path"
+AQUA_MODEL_ARTIFACT_CONFIG_MODEL_TYPE = "model_type"
+AQUA_MODEL_ARTIFACT_FILE = "model_file"
+HF_METADATA_FOLDER = ".cache/"
+HF_LOGIN_DEFAULT_TIMEOUT = 2
+MODEL_NAME_DELIMITER = ";"
+AQUA_TROUBLESHOOTING_LINK = "https://github.com/oracle-samples/oci-data-science-ai-samples/blob/main/ai-quick-actions/troubleshooting-tips.md"
+MODEL_FILE_DESCRIPTION_VERSION = "1.0"
+MODEL_FILE_DESCRIPTION_TYPE = "modelOSSReferenceDescription"
+
+TRAINING_METRICS_FINAL = "training_metrics_final"
+VALIDATION_METRICS_FINAL = "validation_metrics_final"
+TRINING_METRICS = "training_metrics"
+VALIDATION_METRICS = "validation_metrics"
+
+SERVICE_MANAGED_CONTAINER_URI_SCHEME = "dsmc://"
+SUPPORTED_FILE_FORMATS = ["jsonl"]
+MODEL_BY_REFERENCE_OSS_PATH_KEY = "artifact_location"
+
+CONSOLE_LINK_RESOURCE_TYPE_MAPPING = {
+    "datasciencemodel": "models",
+    "datasciencemodeldeployment": "model-deployments",
+    "datasciencemodeldeploymentdev": "model-deployments",
+    "datasciencemodeldeploymentint": "model-deployments",
+    "datasciencemodeldeploymentpre": "model-deployments",
+    "datasciencejob": "jobs",
+    "datasciencejobrun": "job-runs",
+    "datasciencejobrundev": "job-runs",
+    "datasciencejobrunint": "job-runs",
+    "datasciencejobrunpre": "job-runs",
+    "datasciencemodelversionset": "model-version-sets",
+    "datasciencemodelversionsetpre": "model-version-sets",
+    "datasciencemodelversionsetint": "model-version-sets",
+    "datasciencemodelversionsetdev": "model-version-sets",
+}
+
+VLLM_INFERENCE_RESTRICTED_PARAMS = {
+    "--port",
+    "--host",
+    "--served-model-name",
+    "--seed",
+}
+TGI_INFERENCE_RESTRICTED_PARAMS = {
+    "--port",
+    "--hostname",
+    "--num-shard",
+    "--sharded",
+    "--trust-remote-code",
+}
+LLAMA_CPP_INFERENCE_RESTRICTED_PARAMS = {
+    "--port",
+    "--host",
+}
+TEI_CONTAINER_DEFAULT_HOST = "8080"
+
+OCI_OPERATION_FAILURES = {
+    "list_model_deployments": "Unable to list model deployments. See tips for troubleshooting: ",
+    "list_models": "Unable to list models. See tips for troubleshooting: ",
+    "get_namespace": "Unable to access specified Object Storage Bucket. See tips for troubleshooting: ",
+    "list_log_groups": "Unable to access logs. See tips for troubleshooting: ",
+    "list_buckets": "Unable to list Object Storage Bucket. See tips for troubleshooting: ",
+    "put_object": "Unable to access or find Object Storage Bucket. See tips for troubleshooting: ",
+    "list_model_version_sets": "Unable to create or fetch model version set. See tips for troubleshooting:",
+    "update_model": "Unable to update model. See tips for troubleshooting: ",
+    "list_data_science_private_endpoints": "Unable to access private endpoint. See tips for troubleshooting:  ",
+    "create_model": "Unable to register model. See tips for troubleshooting: ",
+    "create_deployment": "Unable to create deployment. See tips for troubleshooting: ",
+    "create_model_version_sets": "Unable to create model version set. See tips for troubleshooting: ",
+    "create_job": "Unable to create job. See tips for troubleshooting: ",
+    "create_job_run": "Unable to create job run. See tips for troubleshooting: ",
+}
+
+STATUS_CODE_MESSAGES = {
+    "400": "Could not process your request due to invalid input.",
+    "403": "We're having trouble processing your request with the information provided.",
+    "404": "Authorization Failed: The resource you're looking for isn't accessible.",
+    "408": "Server is taking too long to respond, please try again.",
+}

ads/aqua/data.py

@@ -0,0 +1,14 @@
+#!/usr/bin/env python
+# Copyright (c) 2024, 2025 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+
+from dataclasses import dataclass
+
+from ads.common.serializer import DataClassSerializable
+
+
+@dataclass(repr=False)
+class AquaResourceIdentifier(DataClassSerializable):
+    id: str = ""
+    name: str = ""
+    url: str = ""

ads/aqua/dummy_data/icon.txt

@@ -0,0 +1 @@
+data:image/svg+xml;base64,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

ads/aqua/dummy_data/oci_model_deployments.json

@@ -0,0 +1,56 @@
+[
+  {
+    "categoryLogDetails": {
+      "access": {
+        "logGroupId": "ocid1.loggroup.oc1.iad.xxxx",
+        "logId": "ocid1.log.oc1.iad.xxxx"
+      },
+      "predict": {
+        "logGroupId": "ocid1.loggroup.oc1.iad.xxxx",
+        "logId": "ocid1.log.oc1.iad.xxxx"
+      }
+    },
+    "compartmentId": "ocid1.compartment.oc1..xxxx",
+    "createdBy": "ocid1.user.oc1..xxxx",
+    "description": "service model 1.",
+    "displayName": "Test deployment of Mock service model 1 via UI",
+    "freeformTags": {
+      "aqua_service_model": "ocid1.datasciencemodel.oc1.iad.xxxx"
+    },
+    "id": "ocid1.datasciencemodeldeployment.oc1.iad.xxxx",
+    "lifecycleDetails": "Model Deployment is Active.",
+    "lifecycleState": "ACTIVE",
+    "modelDeploymentConfigurationDetails": {
+      "deploymentType": "SINGLE_MODEL",
+      "environmentConfigurationDetails": {
+        "entrypoint": [
+          "python",
+          "/opt/api/api.py"
+        ],
+        "environmentConfigurationType": "OCIR_CONTAINER",
+        "healthCheckPort": 5000,
+        "image": "iad.ocir.io/ociodscdev/aqua_deploy:1.0.0",
+        "imageDigest": "sha256:07f43194badef8973b4bd59d649a456b90b57e632f03927896232e904e02cdf1",
+        "serverPort": 5000
+      },
+      "modelConfigurationDetails": {
+        "bandwidthMbps": 10,
+        "instanceConfiguration": {
+          "instanceShapeName": "VM.Standard.E4.Flex",
+          "modelDeploymentInstanceShapeConfigDetails": {
+            "memoryInGBs": 16.0,
+            "ocpus": 1.0
+          }
+        },
+        "modelId": "ocid1.datasciencemodel.oc1.iad.xxxx",
+        "scalingPolicy": {
+          "instanceCount": 1,
+          "policyType": "FIXED_SIZE"
+        }
+      }
+    },
+    "modelDeploymentUrl": "https://modeldeployment.us-ashburn-1.oci.customer-oci.com/ocid1.datasciencemodeldeployment.oc1.iad.xxx",
+    "projectId": "ocid1.datascienceproject.oc1.iad.xxxx",
+    "timeCreated": "2024-01-25T00:26:14.542000Z"
+  }
+]

ads/aqua/dummy_data/oci_models.json

@@ -0,0 +1 @@
+[{"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mistral 7B Instruct", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T17:47:19.488000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"aqua_service_model": "ocid1.datasciencemodel.oc1.iad.xxxx#llama2", "license": "Apache", "task": "text_generation", "organization": "Meta AI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "ModelArtifacts", "value": ".model-ignore, score.py, runtime.yaml, output_schema.json, input_schema.json, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "training environment"}, {"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "training environment"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "training environment"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "training profile"}, {"key": "ClientLibrary", "value": "ADS", "category": "other"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "training environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "training environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "other"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact1", "description": "model by reference storage path", "category": "other"}], "definedMetadataList": [{"key": "UseCaseType", "value": "multinomial_classification"}, {"key": "Algorithm", "value": "None"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}, {"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mock service model 2", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T17:57:39.158000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"aqua_service_model": "ocid1.datasciencemodel.oc1.iad.xxxx#gpt-4", "license": "MIT", "task": "text_generation", "organization": "OpenAI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "ModelArtifacts", "value": ".model-ignore, score.py, runtime.yaml, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "Training Environment"}, {"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "Training Environment"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "Training Environment"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "Training Profile"}, {"key": "ClientLibrary", "value": "ADS", "category": "Other"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "Training Environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "Training Environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "Other"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact2", "description": "model by reference storage path", "category": "other"}], "definedMetadataList": [{"key": "UseCaseType", "value": "multinomial_classification"}, {"key": "FrameworkVersion"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}, {"key": "Hyperparameters"}, {"key": "Algorithm", "value": "None"}, {"key": "Framework"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}, {"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mock fine tuned model 2", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T19:20:57.856000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"license": "MIT", "task": "text_generation", "aqua_fine_tuned_model": "ocid1.datasciencemodel.oc1.iad.xxxx#gpt-4", "organization": "OpenAI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "Training Environment"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "Training Environment"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact_fine_tuned_2", "description": "model by reference storage path", "category": "other"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "Training Profile"}, {"key": "ModelArtifacts", "value": ".model-ignore, test_json_output.json, score.py, runtime.yaml, output_schema.json, input_schema.json, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "Training Environment"}, {"key": "ClientLibrary", "value": "ADS", "category": "Other"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "Training Environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "Training Environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "Other"}], "definedMetadataList": [{"key": "Hyperparameters"}, {"key": "Algorithm", "value": "None"}, {"key": "FrameworkVersion"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}, {"key": "Framework"}, {"key": "UseCaseType", "value": "multinomial_classification"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}, {"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mock copy of service model 2", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T19:25:59.785000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"license": "MIT", "task": "text_generation", "organization": "OpenAI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "Training Environment"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "Training Environment"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact2", "description": "model by reference storage path", "category": "other"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "Training Profile"}, {"key": "ModelArtifacts", "value": ".model-ignore, test_json_output.json, score.py, runtime.yaml, output_schema.json, input_schema.json, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "Training Environment"}, {"key": "ClientLibrary", "value": "ADS", "category": "Other"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "Training Environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "Training Environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "Other"}], "definedMetadataList": [{"key": "Hyperparameters"}, {"key": "Algorithm", "value": "None"}, {"key": "FrameworkVersion"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}, {"key": "Framework"}, {"key": "UseCaseType", "value": "multinomial_classification"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}, {"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mock copy of service model 1", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T19:30:39.452000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"license": "Apache", "task": "text_generation", "organization": "Meta AI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "Training Environment"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "Training Environment"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact1", "description": "model by reference storage path", "category": "other"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "Training Profile"}, {"key": "ModelArtifacts", "value": ".model-ignore, test_json_output.json, score.py, runtime.yaml, output_schema.json, input_schema.json, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "Training Environment"}, {"key": "ClientLibrary", "value": "ADS", "category": "Other"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "Training Environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "Training Environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "Other"}], "definedMetadataList": [{"key": "Hyperparameters"}, {"key": "Algorithm", "value": "None"}, {"key": "FrameworkVersion"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}, {"key": "Framework"}, {"key": "UseCaseType", "value": "multinomial_classification"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}, {"id": "ocid1.datasciencemodel.oc1.iad.xxxx", "compartmentId": "ocid1.compartment.oc1..xxxx", "projectId": "ocid1.datascienceproject.oc1.iad.xxxx", "displayName": "Mock fine tuned model 1", "lifecycleState": "ACTIVE", "timeCreated": "2024-01-19T19:33:58.078000Z", "createdBy": "ocid1.datasciencenotebooksession.oc1.iad.xxxx", "freeformTags": {"license": "Apache", "task": "text_generation", "aqua_fine_tuned_model": "ocid1.datasciencemodel.oc1.iad.xxxx#llama2", "organization": "Meta AI", "OCI_AQUA": ""}, "customMetadataList": [{"key": "EnvironmentType", "value": "data_science", "description": "The conda environment type, can be published or datascience.", "category": "Training Environment"}, {"key": "CondaEnvironment", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The conda environment where the model was trained.", "category": "Training Environment"}, {"key": "Object Storage Path", "value": "oci://ming-dev@ociodscdev/aqua/model_artifact_fine_tuned_1", "description": "model by reference storage path", "category": "other"}, {"key": "ModelSerializationFormat", "value": "pkl", "description": "The model serialization format.", "category": "Training Profile"}, {"key": "ModelArtifacts", "value": ".model-ignore, test_json_output.json, score.py, runtime.yaml, output_schema.json, input_schema.json, model.pkl, icon.txt", "description": "The list of files located in artifacts folder.", "category": "Training Environment"}, {"key": "ClientLibrary", "value": "ADS", "category": "Other"}, {"key": "SlugName", "value": "automlx234_p38_cpu_x86_64_v1", "description": "The slug name of the training conda environment.", "category": "Training Environment"}, {"key": "CondaEnvironmentPath", "value": "oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1", "description": "The URI of the training conda environment.", "category": "Training Environment"}, {"key": "ModelFileName", "value": "model.pkl", "description": "The model file name.", "category": "Other"}], "definedMetadataList": [{"key": "Hyperparameters"}, {"key": "Algorithm", "value": "None"}, {"key": "FrameworkVersion"}, {"key": "ArtifactTestResults", "value": "{\"score_py\": {\"key\": \"score_py\", \"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"score.py\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'score.py' is missing.\", \"success\": true}, \"runtime_yaml\": {\"category\": \"Mandatory Files Check\", \"description\": \"Check that the file \\\"runtime.yaml\\\" exists and is in the top level directory of the artifact directory\", \"error_msg\": \"The file 'runtime.yaml' is missing.\", \"success\": true}, \"score_syntax\": {\"category\": \"score.py\", \"description\": \"Check for Python syntax errors\", \"error_msg\": \"There is Syntax error in score.py: \", \"success\": true}, \"score_load_model\": {\"category\": \"score.py\", \"description\": \"Check that load_model() is defined\", \"error_msg\": \"Function load_model is not present in score.py.\", \"success\": true}, \"score_predict\": {\"category\": \"score.py\", \"description\": \"Check that predict() is defined\", \"error_msg\": \"Function predict is not present in score.py.\", \"success\": true}, \"score_predict_data\": {\"category\": \"score.py\", \"description\": \"Check that the only required argument for predict() is named \\\"data\\\"\", \"error_msg\": \"The predict function in score.py must have a formal argument named 'data'.\", \"success\": true}, \"score_predict_arg\": {\"category\": \"score.py\", \"description\": \"Check that all other arguments in predict() are optional and have default values\", \"error_msg\": \"All formal arguments in the predict function must have default values, except that 'data' argument.\", \"success\": true}, \"runtime_version\": {\"category\": \"runtime.yaml\", \"description\": \"Check that field MODEL_ARTIFACT_VERSION is set to 3.0\", \"error_msg\": \"In runtime.yaml, the key MODEL_ARTIFACT_VERSION must be set to 3.0.\", \"success\": true}, \"runtime_env_python\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION is set to a value of 3.6 or higher\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_PYTHON_VERSION must be set to a value of 3.6 or higher.\", \"success\": true, \"value\": \"3.8\"}, \"runtime_env_path\": {\"category\": \"conda_env\", \"description\": \"Check that field MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is set\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH must have a value.\", \"success\": true, \"value\": \"oci://service-conda-packs@id19sfcrra6z/service_pack/cpu/Oracle_AutoMLx_v23.4_for_CPU_on_Python_3.8/1.0/automlx234_p38_cpu_x86_64_v1\"}, \"runtime_path_exist\": {\"category\": \"conda_env\", \"description\": \"Check that the file path in MODEL_DEPLOYMENT.INFERENCE_ENV_PATH is correct.\", \"error_msg\": \"In runtime.yaml, the key MODEL_DEPLOYMENT.INFERENCE_ENV_PATH does not exist.\", \"success\": true}}"}, {"key": "Framework"}, {"key": "UseCaseType", "value": "multinomial_classification"}], "inputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 40.2, \"standard deviation\": 33.77309909117347, \"sample minimum\": 3.0, \"lower quartile\": 14.75, \"median\": 29.5, \"upper quartile\": 69.5, \"sample maximum\": 94.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}", "outputSchema": "{\"schema\": [{\"dtype\": \"int64\", \"feature_type\": \"Integer\", \"name\": 0, \"domain\": {\"values\": \"Integer\", \"stats\": {\"count\": 10.0, \"mean\": 2642.6, \"standard deviation\": 3482.95000123618, \"sample minimum\": 9.0, \"lower quartile\": 219.25, \"median\": 872.5, \"upper quartile\": 5227.0, \"sample maximum\": 8836.0}, \"constraints\": []}, \"required\": true, \"description\": \"0\", \"order\": 0}], \"version\": \"1.1\"}"}]