Merge branch 'main' of https://github.com/oracle/accelerated-data-science into ODSC-47734/add_support_to_cancel_all_runs

lu-ohai · lu-ohai · commit 435741b5f5ff · 2023-09-28T13:01:04.000-04:00
diff --git a/.gitleaks.toml b/.gitleaks.toml
@@ -13,6 +13,7 @@ useDefault = true
         '''example-password''',
         '''this-is-not-the-secret''',
         '''<redacted>''',
+        '''security_token''',
         # NVIDIA_GPGKEY_SUM from public documentation:
         # https://gitlab.com/nvidia/container-images/cuda/-/blob/master/dist/10.1/centos7/base/Dockerfile
         '''d0664fbbdb8c32356d45de36c5984617217b2d0bef41b93ccecd326ba3b80c87'''
diff --git a/ads/model/artifact_uploader.py b/ads/model/artifact_uploader.py
@@ -10,6 +10,7 @@
 from typing import Dict, Optional
 
 from ads.common import utils
+from ads.common.object_storage_details import ObjectStorageDetails
 from ads.model.common import utils as model_utils
 from ads.model.service.oci_datascience_model import OCIDataScienceModel
 
@@ -29,7 +30,10 @@ def __init__(self, dsc_model: OCIDataScienceModel, artifact_path: str):
         artifact_path: str
             The model artifact location.
         """
-        if not os.path.exists(artifact_path):
+        if not (
+            ObjectStorageDetails.is_oci_path(artifact_path)
+            or os.path.exists(artifact_path)
+        ):
             raise ValueError(f"The `{artifact_path}` does not exist")
 
         self.dsc_model = dsc_model
@@ -45,7 +49,7 @@ def upload(self):
             ) as progress:
                 self.progress = progress
                 self.progress.update("Preparing model artifacts ZIP archive.")
-                self._prepare_artiact_tmp_zip()
+                self._prepare_artifact_tmp_zip()
                 self.progress.update("Uploading model artifacts.")
                 self._upload()
                 self.progress.update(
@@ -55,22 +59,19 @@ def upload(self):
         except Exception:
             raise
         finally:
-            self._remove_artiact_tmp_zip()
+            self._remove_artifact_tmp_zip()
 
-    def _prepare_artiact_tmp_zip(self) -> str:
+    def _prepare_artifact_tmp_zip(self) -> str:
         """Prepares model artifacts ZIP archive.
 
-        Parameters
-        ----------
-        progress: (TqdmProgressBar, optional). Defaults to `None`.
-            The progress indicator.
-
         Returns
         -------
         str
             Path to the model artifact ZIP archive.
         """
-        if os.path.isfile(self.artifact_path) and self.artifact_path.lower().endswith(
+        if ObjectStorageDetails.is_oci_path(self.artifact_path):
+            self.artifact_zip_path = self.artifact_path
+        elif os.path.isfile(self.artifact_path) and self.artifact_path.lower().endswith(
             ".zip"
         ):
             self.artifact_zip_path = self.artifact_path
@@ -80,7 +81,7 @@ def _prepare_artiact_tmp_zip(self) -> str:
             )
         return self.artifact_zip_path
 
-    def _remove_artiact_tmp_zip(self):
+    def _remove_artifact_tmp_zip(self):
         """Removes temporary created artifact zip archive."""
         if (
             self.artifact_zip_path
@@ -112,7 +113,10 @@ class LargeArtifactUploader(ArtifactUploader):
     Attributes
     ----------
     artifact_path: str
-        The model artifact location.
+        The model artifact location. Possible values are:
+            - object storage path to zip archive. Example: `oci://<bucket_name>@<namespace>/prefix/mymodel.zip`.
+            - local path to zip archive. Example: `./mymodel.zip`.
+            - local path to folder with artifacts. Example: `./mymodel`.
     artifact_zip_path: str
         The uri of the zip of model artifact.
     auth: dict
@@ -124,6 +128,8 @@ class LargeArtifactUploader(ArtifactUploader):
         The OCI Object Storage URI where model artifacts will be copied to.
         The `bucket_uri` is only necessary for uploading large artifacts which
         size is greater than 2GB. Example: `oci://<bucket_name>@<namespace>/prefix/`.
+        .. versionadded:: 2.8.10
+        If artifact_path is object storage path to a zip archive, bucket_uri will be ignored.
     dsc_model: OCIDataScienceModel
         The data scince model instance.
     overwrite_existing_artifact: bool
@@ -145,7 +151,7 @@ def __init__(
         self,
         dsc_model: OCIDataScienceModel,
         artifact_path: str,
-        bucket_uri: str,
+        bucket_uri: str = None,
         auth: Optional[Dict] = None,
         region: Optional[str] = None,
         overwrite_existing_artifact: Optional[bool] = True,
@@ -159,11 +165,16 @@ def __init__(
         dsc_model: OCIDataScienceModel
             The data scince model instance.
         artifact_path: str
-            The model artifact location.
-        bucket_uri: str
+            The model artifact location. Possible values are:
+                - object storage path to zip archive. Example: `oci://<bucket_name>@<namespace>/prefix/mymodel.zip`.
+                - local path to zip archive. Example: `./mymodel.zip`.
+                - local path to folder with artifacts. Example: `./mymodel`.
+        bucket_uri: (str, optional). Defaults to `None`.
             The OCI Object Storage URI where model artifacts will be copied to.
-            The `bucket_uri` is only necessary for uploading large artifacts which
+            The `bucket_uri` is only necessary for uploading large artifacts from local which
             size is greater than 2GB. Example: `oci://<bucket_name>@<namespace>/prefix/`.
+            .. versionadded:: 2.8.10
+            If `artifact_path` is object storage path to a zip archive, `bucket_uri` will be ignored.
         auth: (Dict, optional). Defaults to `None`.
             The default authetication is set using `ads.set_auth` API.
             If you need to override the default, use the `ads.common.auth.api_keys` or
@@ -179,11 +190,22 @@ def __init__(
         parallel_process_count: (int, optional).
             The number of worker processes to use in parallel for uploading individual parts of a multipart upload.
         """
+        self.auth = auth or dsc_model.auth
+        if ObjectStorageDetails.is_oci_path(artifact_path):
+            if not artifact_path.endswith(".zip"):
+                raise ValueError(
+                    f"The `artifact_path={artifact_path}` is invalid."
+                    "The remote path for model artifact should be a zip archive, "
+                    "e.g. `oci://<bucket_name>@<namespace>/prefix/mymodel.zip`."
+                )
+            if not utils.is_path_exists(uri=artifact_path, auth=self.auth):
+                raise ValueError(f"The `{artifact_path}` does not exist.")
+            bucket_uri = artifact_path
+
         if not bucket_uri:
             raise ValueError("The `bucket_uri` must be provided.")
 
         super().__init__(dsc_model=dsc_model, artifact_path=artifact_path)
-        self.auth = auth or dsc_model.auth
         self.region = region or utils.extract_region(self.auth)
         self.bucket_uri = bucket_uri
         self.overwrite_existing_artifact = overwrite_existing_artifact
@@ -192,38 +214,38 @@ def __init__(
 
     def _upload(self):
         """Uploads model artifacts to the model catalog."""
-        self.progress.update("Copying model artifact to the Object Storage bucket")
-
         bucket_uri = self.bucket_uri
-        bucket_uri_file_name = os.path.basename(bucket_uri)
-
-        if not bucket_uri_file_name:
-            bucket_uri = os.path.join(bucket_uri, f"{self.dsc_model.id}.zip")
-        elif not bucket_uri.lower().endswith(".zip"):
-            bucket_uri = f"{bucket_uri}.zip"
-
-        if not self.overwrite_existing_artifact and utils.is_path_exists(
-            uri=bucket_uri, auth=self.auth
-        ):
-            raise FileExistsError(
-                f"The bucket_uri=`{self.bucket_uri}` exists. Please use a new file name or "
-                "set `overwrite_existing_artifact` to `True` if you wish to overwrite."
-            )
+        self.progress.update("Copying model artifact to the Object Storage bucket")
+        if not bucket_uri == self.artifact_zip_path:
+            bucket_uri_file_name = os.path.basename(bucket_uri)
+
+            if not bucket_uri_file_name:
+                bucket_uri = os.path.join(bucket_uri, f"{self.dsc_model.id}.zip")
+            elif not bucket_uri.lower().endswith(".zip"):
+                bucket_uri = f"{bucket_uri}.zip"
+
+            if not self.overwrite_existing_artifact and utils.is_path_exists(
+                uri=bucket_uri, auth=self.auth
+            ):
+                raise FileExistsError(
+                    f"The bucket_uri=`{self.bucket_uri}` exists. Please use a new file name or "
+                    "set `overwrite_existing_artifact` to `True` if you wish to overwrite."
+                )
 
-        try:
-            utils.upload_to_os(
-                src_uri=self.artifact_zip_path,
-                dst_uri=bucket_uri,
-                auth=self.auth,
-                parallel_process_count=self._parallel_process_count,
-                force_overwrite=self.overwrite_existing_artifact,
-                progressbar_description="Copying model artifact to the Object Storage bucket.",
-            )
-        except Exception as ex:
-            raise RuntimeError(
-                f"Failed to upload model artifact to the given Object Storage path `{self.bucket_uri}`."
-                f"See Exception: {ex}"
-            )
+            try:
+                utils.upload_to_os(
+                    src_uri=self.artifact_zip_path,
+                    dst_uri=bucket_uri,
+                    auth=self.auth,
+                    parallel_process_count=self._parallel_process_count,
+                    force_overwrite=self.overwrite_existing_artifact,
+                    progressbar_description="Copying model artifact to the Object Storage bucket.",
+                )
+            except Exception as ex:
+                raise RuntimeError(
+                    f"Failed to upload model artifact to the given Object Storage path `{self.bucket_uri}`."
+                    f"See Exception: {ex}"
+                )
 
         self.progress.update("Exporting model artifact to the model catalog")
         self.dsc_model.export_model_artifact(bucket_uri=bucket_uri, region=self.region)
diff --git a/ads/model/datascience_model.py b/ads/model/datascience_model.py
@@ -11,6 +11,7 @@
 
 import pandas
 from ads.common import utils
+from ads.common.object_storage_details import ObjectStorageDetails
 from ads.config import COMPARTMENT_OCID, PROJECT_OCID
 from ads.feature_engineering.schema import Schema
 from ads.jobs.builders.base import Builder
@@ -548,6 +549,8 @@ def create(self, **kwargs) -> "DataScienceModel":
                 The OCI Object Storage URI where model artifacts will be copied to.
                 The `bucket_uri` is only necessary for uploading large artifacts which
                 size is greater than 2GB. Example: `oci://<bucket_name>@<namespace>/prefix/`.
+                .. versionadded:: 2.8.10
+                If `artifact` is provided as an object storage path to a zip archive, `bucket_uri` will be ignored.
             overwrite_existing_artifact: (bool, optional). Defaults to `True`.
                 Overwrite target bucket artifact if exists.
             remove_existing_artifact: (bool, optional). Defaults to `True`.
@@ -636,6 +639,8 @@ def upload_artifact(
             The OCI Object Storage URI where model artifacts will be copied to.
             The `bucket_uri` is only necessary for uploading large artifacts which
             size is greater than 2GB. Example: `oci://<bucket_name>@<namespace>/prefix/`.
+            .. versionadded:: 2.8.10
+            If `artifact` is provided as an object storage path to a zip archive, `bucket_uri` will be ignored.
         auth: (Dict, optional). Defaults to `None`.
             The default authentication is set using `ads.set_auth` API.
             If you need to override the default, use the `ads.common.auth.api_keys` or
@@ -668,6 +673,13 @@ def upload_artifact(
                 "timeout": timeout,
             }
 
+        if ObjectStorageDetails.is_oci_path(self.artifact):
+            if bucket_uri and bucket_uri != self.artifact:
+                logger.warn(
+                    "The `bucket_uri` will be ignored and the value of `self.artifact` will be used instead."
+                )
+            bucket_uri = self.artifact
+
         if bucket_uri or utils.folder_size(self.artifact) > _MAX_ARTIFACT_SIZE_IN_BYTES:
             if not bucket_uri:
                 raise ModelArtifactSizeError(
diff --git a/ads/model/model_artifact_boilerplate/artifact_introspection_test/model_artifact_validate.py b/ads/model/model_artifact_boilerplate/artifact_introspection_test/model_artifact_validate.py
@@ -30,7 +30,7 @@
 HTML_PATH = os.path.join(_cwd, "resources", "template.html")
 CONFIG_PATH = os.path.join(_cwd, "resources", "config.yaml")
 PYTHON_VER_PATTERN = "^([3])(\.[6-9])(\.\d+)?$"
-PAR_URL = "https://objectstorage.us-ashburn-1.oraclecloud.com/p/Ri7zFc_h91sxMdgnza9Qnqw3Ina8hf8wzDvEpAnUXMDOnUR1U1fpsaBUjUfgPgIq/n/ociodscdev/b/service-conda-packs/o/service_pack/index.json"
+PAR_URL = "https://objectstorage.us-ashburn-1.oraclecloud.com/p/WyjtfVIG0uda-P3-2FmAfwaLlXYQZbvPZmfX1qg0-sbkwEQO6jpwabGr2hMDBmBp/n/ociodscdev/b/service-conda-packs/o/service_pack/index.json"
 
 TESTS = {
     "score_py": {
@@ -195,7 +195,9 @@ def check_runtime_yml(file_path) -> Tuple[bool, str]:
                         return False, TESTS["runtime_path_exist"]["error_msg"]
                 else:
                     TESTS["runtime_path_exist"]["success"] = False
-                    return False, TESTS["runtime_path_exist"]["error_msg"]
+                    TESTS["runtime_path_exist"][
+                        "error_msg"
+                    ] = "WARNING: Unable to validate if INFERENCE_ENV_PATH exists. Please check if you have internet access."
             else:
                 bucket_name = env_path.username
                 namespace = env_path.hostname
diff --git a/docs/source/release_notes.rst b/docs/source/release_notes.rst
@@ -2,12 +2,24 @@
 Release Notes
 =============
 
+2.8.10
+------
+Release date: September 27, 2023
+
+* Improved the ``LargeArtifactUploader`` class to understand OCI paths to upload model artifacts to the model catalog by reference.
+* Removed ``ADSDataset`` runtime dependency on ``geopandas``.
+* Fixed a bug in the progress bar during model registration.
+* Fixed a bug where session variable could be referenced before assignment.
+* Fixed a bug with model artifact save.
+* Fixed a bug with pipelines step.
+
 2.8.9
 -----
 Release date: September 5, 2023
 
 * Upgraded the ``scikit-learn`` dependency to ``>=1.0``.
 * Upgraded the ``pandas`` dependency to ``>1.2.1,<2.1`` to allow you to use ADS with pandas 2.0.
+* Implemented multi-part upload in the ``ArtifactUploader`` to upload model artifacts to the model catalog.
 * Fixed the "Attribute not found" error, when ``deploy()`` called twice in ``GenericModel``.
 * Fixed the fetch of the security token, when the relative path for the ``security_token_file`` is provided (used in session token-bases authentication).
 
diff --git a/pyproject.toml b/pyproject.toml
@@ -19,7 +19,7 @@ build-backend = "flit_core.buildapi"
 
 # Required
 name = "oracle_ads"  # the install (PyPI) name; name for local build in [tool.flit.module] section below
-version = "2.8.9"
+version = "2.8.10"
 
 # Optional
 description = "Oracle Accelerated Data Science SDK"
@@ -57,7 +57,7 @@ dependencies = [
   "asteval>=0.9.25",
   "cerberus>=1.3.4",
   "cloudpickle>=1.6.0",
-  "fsspec>=0.8.7,<2023.9.1",  # v2.9.1 introduced issues, releved by unit tests
+  "fsspec>=0.8.7,<2023.9.1",  # v2.9.1 introduced issues, revealed by unit tests
   "gitpython>=3.1.2",
   "jinja2>=2.11.2",
   "matplotlib>=3.1.3",
@@ -109,7 +109,7 @@ onnx = [
   "lightgbm==3.3.1",
   "onnx>=1.12.0",
   "onnxmltools>=1.10.0",
-  "onnxruntime>=1.10.0,<1.16",  # v1.16 introduced issues https://github.com/microsoft/onnxruntime/issues/17631, releved by unit tests
+  "onnxruntime>=1.10.0,<1.16",  # v1.16 introduced issues https://github.com/microsoft/onnxruntime/issues/17631, revealedd by unit tests
   "oracle_ads[viz]",
   "protobuf<=3.20",
   "skl2onnx>=1.10.4",
diff --git a/tests/unitary/default_setup/model/test_artifact_uploader.py b/tests/unitary/default_setup/model/test_artifact_uploader.py
