acryl-datahub-cloud 0.3.7.9.1__tar.gz → 0.3.7.10rc1__tar.gz

{acryl_datahub_cloud-0.3.7.9.1 → acryl_datahub_cloud-0.3.7.10rc1}/PKG-INFO

@@ -1,82 +1,82 @@
 Metadata-Version: 2.2
 Name: acryl-datahub-cloud
-Version: 0.3.7.9.1
+Version: 0.3.7.10rc1
 Requires-Dist: avro-gen3==0.7.16
 Requires-Dist: acryl-datahub
 Provides-Extra: datahub-lineage-features
-Requires-Dist: opensearch-py==2.4.2; extra == "datahub-lineage-features"
 Requires-Dist: pyarrow; extra == "datahub-lineage-features"
 Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
-Requires-Dist: pandas; extra == "datahub-lineage-features"
 Requires-Dist: duckdb; extra == "datahub-lineage-features"
+Requires-Dist: pandas; extra == "datahub-lineage-features"
+Requires-Dist: opensearch-py==2.4.2; extra == "datahub-lineage-features"
 Provides-Extra: datahub-reporting-forms
 Requires-Dist: pyarrow; extra == "datahub-reporting-forms"
 Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
+Requires-Dist: duckdb; extra == "datahub-reporting-forms"
 Requires-Dist: boto3; extra == "datahub-reporting-forms"
 Requires-Dist: pandas; extra == "datahub-reporting-forms"
-Requires-Dist: duckdb; extra == "datahub-reporting-forms"
 Provides-Extra: datahub-reporting-extract-graph
-Requires-Dist: opensearch-py==2.4.2; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
+Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
-Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
+Requires-Dist: opensearch-py==2.4.2; extra == "datahub-reporting-extract-graph"
 Provides-Extra: datahub-reporting-extract-sql
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
+Requires-Dist: duckdb; extra == "datahub-reporting-extract-sql"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
-Requires-Dist: duckdb; extra == "datahub-reporting-extract-sql"
 Provides-Extra: datahub-usage-feature-reporting
-Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-feature-reporting"
-Requires-Dist: pandas; extra == "datahub-usage-feature-reporting"
-Requires-Dist: duckdb; extra == "datahub-usage-feature-reporting"
-Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-feature-reporting"
-Requires-Dist: numpy<2; extra == "datahub-usage-feature-reporting"
 Requires-Dist: pyarrow; extra == "datahub-usage-feature-reporting"
-Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-feature-reporting"
 Requires-Dist: pydantic<2; extra == "datahub-usage-feature-reporting"
-Requires-Dist: boto3; extra == "datahub-usage-feature-reporting"
 Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-feature-reporting"
+Requires-Dist: duckdb; extra == "datahub-usage-feature-reporting"
+Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-feature-reporting"
+Requires-Dist: boto3; extra == "datahub-usage-feature-reporting"
+Requires-Dist: pandas; extra == "datahub-usage-feature-reporting"
+Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-feature-reporting"
+Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-feature-reporting"
+Requires-Dist: numpy<2; extra == "datahub-usage-feature-reporting"
 Requires-Dist: polars<=1.16.0; extra == "datahub-usage-feature-reporting"
 Provides-Extra: acryl-cs-issues
-Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Requires-Dist: jinja2; extra == "acryl-cs-issues"
-Requires-Dist: openai; extra == "acryl-cs-issues"
+Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Requires-Dist: zenpy; extra == "acryl-cs-issues"
+Requires-Dist: openai; extra == "acryl-cs-issues"
 Provides-Extra: all
+Requires-Dist: pyarrow; extra == "all"
+Requires-Dist: pydantic<2; extra == "all"
+Requires-Dist: elasticsearch==7.13.4; extra == "all"
+Requires-Dist: duckdb; extra == "all"
+Requires-Dist: scipy<=1.14.1; extra == "all"
+Requires-Dist: boto3; extra == "all"
+Requires-Dist: pandas; extra == "all"
 Requires-Dist: opensearch-py==2.4.2; extra == "all"
-Requires-Dist: jinja2; extra == "all"
+Requires-Dist: zenpy; extra == "all"
 Requires-Dist: openai; extra == "all"
-Requires-Dist: pandas; extra == "all"
-Requires-Dist: duckdb; extra == "all"
+Requires-Dist: slack-sdk; extra == "all"
+Requires-Dist: jinja2; extra == "all"
 Requires-Dist: pyarrow<=18.0.0; extra == "all"
-Requires-Dist: zenpy; extra == "all"
 Requires-Dist: numpy<2; extra == "all"
-Requires-Dist: slack-sdk; extra == "all"
-Requires-Dist: pyarrow; extra == "all"
-Requires-Dist: scipy<=1.14.1; extra == "all"
-Requires-Dist: pydantic<2; extra == "all"
-Requires-Dist: boto3; extra == "all"
-Requires-Dist: elasticsearch==7.13.4; extra == "all"
 Requires-Dist: polars<=1.16.0; extra == "all"
 Provides-Extra: dev
+Requires-Dist: pyarrow; extra == "dev"
+Requires-Dist: pydantic<2; extra == "dev"
+Requires-Dist: elasticsearch==7.13.4; extra == "dev"
+Requires-Dist: duckdb; extra == "dev"
+Requires-Dist: scipy<=1.14.1; extra == "dev"
+Requires-Dist: boto3; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
 Requires-Dist: opensearch-py==2.4.2; extra == "dev"
-Requires-Dist: jinja2; extra == "dev"
+Requires-Dist: zenpy; extra == "dev"
 Requires-Dist: openai; extra == "dev"
-Requires-Dist: pandas; extra == "dev"
-Requires-Dist: duckdb; extra == "dev"
-Requires-Dist: pyarrow<=18.0.0; extra == "dev"
+Requires-Dist: slack-sdk; extra == "dev"
+Requires-Dist: jinja2; extra == "dev"
 Requires-Dist: acryl-datahub[dev]; extra == "dev"
-Requires-Dist: zenpy; extra == "dev"
+Requires-Dist: pyarrow<=18.0.0; extra == "dev"
 Requires-Dist: numpy<2; extra == "dev"
-Requires-Dist: slack-sdk; extra == "dev"
-Requires-Dist: pyarrow; extra == "dev"
-Requires-Dist: scipy<=1.14.1; extra == "dev"
-Requires-Dist: pydantic<2; extra == "dev"
-Requires-Dist: boto3; extra == "dev"
-Requires-Dist: elasticsearch==7.13.4; extra == "dev"
 Requires-Dist: polars<=1.16.0; extra == "dev"
 Dynamic: provides-extra
 Dynamic: requires-dist

{acryl_datahub_cloud-0.3.7.9.1 → acryl_datahub_cloud-0.3.7.10rc1}/src/acryl_datahub_cloud/_codegen_config.json

@@ -1,6 +1,6 @@
 {
   "name": "acryl-datahub-cloud",
-  "version": "0.3.7.9.1",
+  "version": "0.3.7.10rc1",
   "install_requires": [
     "avro-gen3==0.7.16",
     "acryl-datahub"

{acryl_datahub_cloud-0.3.7.9.1 → acryl_datahub_cloud-0.3.7.10rc1}/src/acryl_datahub_cloud/metadata/com/linkedin/pegasus2avro/ml/metadata/__init__.py

@@ -30,7 +30,6 @@ from ......schema_classes import MLModelFactorsClass
 from ......schema_classes import MLModelGroupPropertiesClass
 from ......schema_classes import MLModelPropertiesClass
 from ......schema_classes import MLPrimaryKeyPropertiesClass
-from ......schema_classes import MLTrainingRunPropertiesClass
 from ......schema_classes import MetricsClass
 from ......schema_classes import QuantitativeAnalysesClass
 from ......schema_classes import SourceCodeClass
@@ -62,7 +61,6 @@ MLModelFactors = MLModelFactorsClass
 MLModelGroupProperties = MLModelGroupPropertiesClass
 MLModelProperties = MLModelPropertiesClass
 MLPrimaryKeyProperties = MLPrimaryKeyPropertiesClass
-MLTrainingRunProperties = MLTrainingRunPropertiesClass
 Metrics = MetricsClass
 QuantitativeAnalyses = QuantitativeAnalysesClass
 SourceCode = SourceCodeClass

{acryl_datahub_cloud-0.3.7.9.1 → acryl_datahub_cloud-0.3.7.10rc1}/src/acryl_datahub_cloud/metadata/schema.avsc

@@ -16044,66 +16044,6 @@
         "default": null,
         "doc": "URL where the reference exist"
       },
-      {
-        "Relationship": {
-          "/*": {
-            "entityTypes": [
-              "dataJob",
-              "dataProcessInstance"
-            ],
-            "isLineage": true,
-            "name": "TrainedBy"
-          }
-        },
-        "type": [
-          "null",
-          {
-            "type": "array",
-            "items": "string"
-          }
-        ],
-        "name": "trainingJobs",
-        "default": null,
-        "doc": "List of jobs or process instances (if any) used to train the model or group. Visible in Lineage. Note that ML Models can also be specified as the output of a specific Data Process Instances (runs) via the DataProcessInstanceOutputs aspect."
-      },
-      {
-        "Relationship": {
-          "/*": {
-            "entityTypes": [
-              "dataJob",
-              "dataProcessInstance"
-            ],
-            "isLineage": true,
-            "isUpstream": false,
-            "name": "UsedBy"
-          }
-        },
-        "type": [
-          "null",
-          {
-            "type": "array",
-            "items": "string"
-          }
-        ],
-        "name": "downstreamJobs",
-        "default": null,
-        "doc": "List of jobs or process instances (if any) that use the model or group."
-      },
-      {
-        "Searchable": {
-          "boostScore": 10.0,
-          "enableAutocomplete": true,
-          "fieldType": "WORD_GRAM",
-          "queryByDefault": true
-        },
-        "type": [
-          "null",
-          "string"
-        ],
-        "name": "name",
-        "default": null,
-        "doc": "Display name of the MLModel"
-      },
       {
         "Searchable": {
           "fieldType": "TEXT",
@@ -16118,7 +16058,6 @@
         "doc": "Documentation of the MLModel"
       },
       {
-        "deprecated": true,
         "type": [
           "null",
           "long"
@@ -16127,24 +16066,6 @@
         "default": null,
         "doc": "Date when the MLModel was developed"
       },
-      {
-        "type": [
-          "null",
-          "com.linkedin.pegasus2avro.common.TimeStamp"
-        ],
-        "name": "created",
-        "default": null,
-        "doc": "Audit stamp containing who created this and when"
-      },
-      {
-        "type": [
-          "null",
-          "com.linkedin.pegasus2avro.common.TimeStamp"
-        ],
-        "name": "lastModified",
-        "default": null,
-        "doc": "Date when the MLModel was last modified"
-      },
       {
         "type": [
           "null",
@@ -16320,11 +16241,10 @@
         "Relationship": {
           "/*": {
             "entityTypes": [
-              "mlModelGroup"
+              "dataJob"
             ],
             "isLineage": true,
-            "isUpstream": false,
-            "name": "MemberOf"
+            "name": "TrainedBy"
           }
         },
         "Urn": "Urn",
@@ -16336,62 +16256,23 @@
             "items": "string"
           }
         ],
-        "name": "groups",
+        "name": "trainingJobs",
         "default": null,
-        "doc": "Groups the model belongs to"
-      }
-    ],
-    "doc": "Properties associated with a ML Model"
-  },
-  {
-    "type": "record",
-    "Aspect": {
-      "name": "mlTrainingRunProperties"
-    },
-    "name": "MLTrainingRunProperties",
-    "namespace": "com.linkedin.pegasus2avro.ml.metadata",
-    "fields": [
+        "doc": "List of jobs (if any) used to train the model"
+      },
       {
-        "Searchable": {
+        "Relationship": {
           "/*": {
-            "fieldType": "TEXT",
-            "queryByDefault": true
+            "entityTypes": [
+              "dataJob"
+            ],
+            "isLineage": true,
+            "isUpstream": false,
+            "name": "UsedBy"
           }
         },
-        "type": {
-          "type": "map",
-          "values": "string"
-        },
-        "name": "customProperties",
-        "default": {},
-        "doc": "Custom property bag."
-      },
-      {
-        "Searchable": {
-          "fieldType": "KEYWORD"
-        },
-        "java": {
-          "class": "com.linkedin.pegasus2avro.common.url.Url",
-          "coercerClass": "com.linkedin.pegasus2avro.common.url.UrlCoercer"
-        },
-        "type": [
-          "null",
-          "string"
-        ],
-        "name": "externalUrl",
-        "default": null,
-        "doc": "URL where the reference exist"
-      },
-      {
-        "type": [
-          "null",
-          "string"
-        ],
-        "name": "id",
-        "default": null,
-        "doc": "Run Id of the ML Training Run"
-      },
-      {
+        "Urn": "Urn",
+        "urn_is_array": true,
         "type": [
           "null",
           {
@@ -16399,36 +16280,36 @@
             "items": "string"
           }
         ],
-        "name": "outputUrls",
+        "name": "downstreamJobs",
         "default": null,
-        "doc": "List of URLs for the Outputs of the ML Training Run"
+        "doc": "List of jobs (if any) that use the model"
       },
       {
-        "type": [
-          "null",
-          {
-            "type": "array",
-            "items": "com.linkedin.pegasus2avro.ml.metadata.MLHyperParam"
+        "Relationship": {
+          "/*": {
+            "entityTypes": [
+              "mlModelGroup"
+            ],
+            "isLineage": true,
+            "isUpstream": false,
+            "name": "MemberOf"
           }
-        ],
-        "name": "hyperParams",
-        "default": null,
-        "doc": "Hyperparameters of the ML Training Run"
-      },
-      {
+        },
+        "Urn": "Urn",
+        "urn_is_array": true,
         "type": [
           "null",
           {
             "type": "array",
-            "items": "com.linkedin.pegasus2avro.ml.metadata.MLMetric"
+            "items": "string"
           }
         ],
-        "name": "trainingMetrics",
+        "name": "groups",
         "default": null,
-        "doc": "Metrics of the ML Training Run"
+        "doc": "Groups the model belongs to"
       }
     ],
-    "doc": "The inputs and outputs of this training run"
+    "doc": "Properties associated with a ML Model"
   },
   {
     "type": "record",
@@ -17223,66 +17104,6 @@
         "default": {},
         "doc": "Custom property bag."
       },
-      {
-        "Relationship": {
-          "/*": {
-            "entityTypes": [
-              "dataJob",
-              "dataProcessInstance"
-            ],
-            "isLineage": true,
-            "name": "TrainedBy"
-          }
-        },
-        "type": [
-          "null",
-          {
-            "type": "array",
-            "items": "string"
-          }
-        ],
-        "name": "trainingJobs",
-        "default": null,
-        "doc": "List of jobs or process instances (if any) used to train the model or group. Visible in Lineage. Note that ML Models can also be specified as the output of a specific Data Process Instances (runs) via the DataProcessInstanceOutputs aspect."
-      },
-      {
-        "Relationship": {
-          "/*": {
-            "entityTypes": [
-              "dataJob",
-              "dataProcessInstance"
-            ],
-            "isLineage": true,
-            "isUpstream": false,
-            "name": "UsedBy"
-          }
-        },
-        "type": [
-          "null",
-          {
-            "type": "array",
-            "items": "string"
-          }
-        ],
-        "name": "downstreamJobs",
-        "default": null,
-        "doc": "List of jobs or process instances (if any) that use the model or group."
-      },
-      {
-        "Searchable": {
-          "boostScore": 10.0,
-          "enableAutocomplete": true,
-          "fieldType": "WORD_GRAM",
-          "queryByDefault": true
-        },
-        "type": [
-          "null",
-          "string"
-        ],
-        "name": "name",
-        "default": null,
-        "doc": "Display name of the MLModelGroup"
-      },
       {
         "Searchable": {
           "fieldType": "TEXT",
@@ -17297,7 +17118,6 @@
         "doc": "Documentation of the MLModelGroup"
       },
       {
-        "deprecated": true,
         "type": [
           "null",
           "long"
@@ -17306,24 +17126,6 @@
         "default": null,
         "doc": "Date when the MLModelGroup was developed"
       },
-      {
-        "type": [
-          "null",
-          "com.linkedin.pegasus2avro.common.TimeStamp"
-        ],
-        "name": "created",
-        "default": null,
-        "doc": "Time and Actor who created the MLModelGroup"
-      },
-      {
-        "type": [
-          "null",
-          "com.linkedin.pegasus2avro.common.TimeStamp"
-        ],
-        "name": "lastModified",
-        "default": null,
-        "doc": "Date when the MLModelGroup was last modified"
-      },
       {
         "type": [
           "null",
@@ -20368,6 +20170,7 @@
     "namespace": "com.linkedin.pegasus2avro.post",
     "fields": [
       {
+        "Searchable": {},
         "type": {
           "type": "enum",
           "symbolDocs": {
@@ -20523,9 +20326,20 @@
             "dataset",
             "schemaField",
             "chart",
+            "container",
             "dashboard",
             "dataFlow",
             "dataJob",
+            "dataProduct",
+            "glossaryTerm",
+            "glossaryNode",
+            "mlModel",
+            "mlFeature",
+            "notebook",
+            "mlFeatureTable",
+            "mlPrimaryKey",
+            "mlModelGroup",
+            "domain",
             "dataProduct"
           ],
           "name": "PostTarget"
@@ -20539,9 +20353,20 @@
           "dataset",
           "schemaField",
           "chart",
+          "container",
           "dashboard",
           "dataFlow",
           "dataJob",
+          "dataProduct",
+          "glossaryTerm",
+          "glossaryNode",
+          "mlModel",
+          "mlFeature",
+          "notebook",
+          "mlFeatureTable",
+          "mlPrimaryKey",
+          "mlModelGroup",
+          "domain",
           "dataProduct"
         ],
         "type": [
@@ -20970,10 +20795,8 @@
         "Relationship": {
           "/*": {
             "entityTypes": [
-              "dataset",
-              "mlModel"
+              "dataset"
             ],
-            "isLineage": true,
             "name": "Consumes"
           }
         },
@@ -20993,7 +20816,7 @@
           "items": "string"
         },
         "name": "inputs",
-        "doc": "Input assets consumed"
+        "doc": "Input datasets to be consumed"
       }
     ],
     "doc": "Information about the inputs datasets of a Data process"
@@ -21010,11 +20833,8 @@
         "Relationship": {
           "/*": {
             "entityTypes": [
-              "dataset",
-              "mlModel"
+              "dataset"
             ],
-            "isLineage": true,
-            "isUpstream": false,
             "name": "Produces"
           }
         },
@@ -24096,10 +23916,6 @@
         "dataProcessInstanceRunEvent",
         "status",
         "testResults",
-        "dataPlatformInstance",
-        "subTypes",
-        "container",
-        "mlTrainingRunProperties",
         "lineageFeatures"
       ],
       "entityDoc": "DataProcessInstance represents an instance of a datajob/jobflow run"