teradataml 20.0.0.3__py3-none-any.whl → 20.0.0.4__py3-none-any.whl

teradataml/data/jsons/byom/onnxembeddings.json

@@ -0,0 +1,266 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "1",
+  "function_name": "ONNXEmbeddings",
+  "function_version": "1.0",
+  "function_type": "byom",
+  "function_r_name": "aa.onnx.embeddings",
+  "function_alias_name": "ONNXEmbeddings",
+  "short_description": "This Function generates embeddings values using an ONNX model in Vantage",
+  "long_description": "This function is used to calculate embeddings values in Vantage with a  HuggingFace model that has been created outside Vantage and exported to vantage using ONNX format",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny",
+        "PartitionByKey"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The input table that contains the text from which we generate embedding values ",
+      "description": "The input table that contains the text from which we generate embedding values ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "newdata",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The model table to be used for calculating embedding values ",
+      "description": "The model table to be used for calculating embedding values ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "modeldata",
+      "useInR": true,
+      "rOrderNum": 2
+    },
+    {
+      "requiredInputKind": [
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "partitionByOneInclusive": false,
+      "name": "TokenizerTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The tokenizer table which contains the tokenizer json file ",
+      "description": "The tokenizer table which contains the tokenizer json file ",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "tokenizerdata",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "Accumulate",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the names of input_table columns to copy to the output table.",
+      "description": "Specify the names of the input columns to copy to the output table. ",
+      "datatype": "COLUMNS",
+      "allowsLists": true,
+      "rName": "accumulate",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "ModelOutputTensor",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column of the model's possible output fields that the user wants to calculate and output ",
+      "description": "Specifies the column of the model's possible output fields that the user wants to calculate and output ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "model.output.tensor",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "defaultValue": 512,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "EncodeMaxLength",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the maximum length of the tokenizer output token encodings(only applies for models with symbolic dimensions) ",
+      "description": "Specifies the maximum length of the tokenizer output token encodings(only applies for models with symbolic dimensions) ",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "encode.max.length",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "defaultValue": false,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "ShowModelProperties",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": " Show default or expanded ModelInputFieldsMap based on input model for defaults or ModelInputFieldsMap for expansion. ",
+      "description": " Show default or expanded ModelInputFieldsMap based on input model for defaults or ModelInputFieldsMap for expansion. ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "show.model.properties",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": "emb_",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OutputColumnPrefix",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the column prefix for each of the output columns when using FLOAT32 OutputFormat ",
+      "description": "Specifies the column prefix for each of the output columns when using FLOAT32 OutputFormat ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "output.column.prefix",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": "VARBYTE(3072)",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OutputFormat",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the output format for the model embeddings output ",
+      "description": "Specifies the output format for the model embeddings output ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "output.format",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "permittedValues": [
+        "true",
+        "t",
+        "yes",
+        "y",
+        "1",
+        "false",
+        "f",
+        "no",
+        "n",
+        "0",
+        "*",
+        "current_cached_model"
+      ],
+      "defaultValue": "false",
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "OverwriteCachedModel",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specifies the model name that needs to be removed from the cache. * can also be used to remove the models ",
+      "description": " Specifies the model name that needs to be removed from the cache. * can also be used to remove the models ",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "overwrite.cached.models",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "defaultValue": false,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "IsDebug",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Print additional information in trace table regarding execution of ONNXPredict ",
+      "description": " Print additional information in trace table regarding execution of ONNXPredict ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "is.debug",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "defaultValue": true,
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "ALL"
+      ],
+      "matchLengthOfArgument": "",
+      "allowPadding": true,
+      "name": "EnableMemoryCheck",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "If true, verifies if there is enough native memory for large models ",
+      "description": "If true, verifies if there is enough native memory for large models ",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "enable.memory.check",
+      "useInR": true,
+      "rOrderNum": 12
+    }
+  ]
+}

teradataml/data/jsons/sqle/17.20/TD_Shap.json

@@ -96,7 +96,6 @@
       "name": "TrainingFunction",
       "isRequired": true,
       "datatype": "STRING",
-      "defaultValue": "TD_GLM",
       "isOutputColumn": false,
       "alternateNames": [],
       "rDescription": "Specifies the model type name.",

teradataml/data/jsons/sqle/20.00/TD_HNSW.json

@@ -0,0 +1,296 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "1",
+  "json_content_version": "1",
+  "function_name": "TD_HNSW",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Model Training",
+  "function_alias_name": "TD_HNSW",
+  "function_r_name": "td.hnsw",
+  "short_description": "The TD_HNSW function generates the HNSW model using the input data points which is then used by TD_HNSWPredict function for determining the approximate nearest neighbors for any given input data point.",
+  "long_description": "The TD_HNSW function generates the HNSW model using the input data points which is then used by TD_HNSWPredict function for determining the approximate nearest neighbors for any given input data point.",
+  "input_tables": [
+    {
+      "requiredInputKind": [
+        "PartitionByAny",
+        "Dimension"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "The table that contains the input dataset for HNSW model training/update/delete operation.",
+      "description": "The table that contains the input dataset for HNSW model training/update/delete operation.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    },
+    {
+      "requiredInputKind": [
+        "PartitionByAny"
+      ],
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputModelTable",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "The table that contains the HNSW model for update/delete operation.",
+      "description": "The table that contains the HNSW model for update/delete operation.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "object",
+      "useInR": true,
+      "rOrderNum": 2
+    }
+  ],
+  "output_tables": [
+    {
+      "isOutputTable": true,
+      "omitPossible": false,
+      "name": "ModelTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the name of the table in which the generated HNSW model can be stored.",
+      "description": "Specifies the name of the table in which the generated HNSW model can be stored.",
+      "datatype": "TABLE_NAME",
+      "allowsLists": false,
+      "rName": "model.table",
+      "useInR": true,
+      "rOrderNum": 3
+    }
+  ],
+  "argument_clauses": [
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "INTEGER"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "IdColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specify the column name containing unique identifier of input rows.",
+      "description": "Specify the column name containing unique identifier of input rows.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "id.column",
+      "useInR": true,
+      "rOrderNum": 4
+    },
+    {
+      "targetTable": [
+        "InputTable"
+      ],
+      "checkDuplicate": true,
+      "allowedTypes": [],
+      "allowedTypeGroups": [
+        "VECTOR","BYTE","VARBYTE"
+      ],
+      "requiredLength": 1,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "VectorColumn",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the column from the input table to be used for training the HNSW model.",
+      "description": "Specifies the column from the input table to be used for training the HNSW model.",
+      "datatype": "COLUMN_NAMES",
+      "allowsLists": false,
+      "rName": "vector.column",
+      "useInR": true,
+      "rOrderNum": 5
+    },
+    {
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumLayer",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the maximum number of layers for the HNSW model.",
+      "description": "Specify the maximum number of layers for the HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "num.layer",
+      "useInR": true,
+      "rOrderNum": 6
+    },
+    {
+      "lowerBound": 0,
+      "upperBound": 2147483647,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "Seed",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the random seed value for repeatable results.",
+      "description": "Specify the random seed value for repeatable results.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "seed",
+      "useInR": true,
+      "rOrderNum": 7
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EfConstruction",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the number of neighbors to search during training of HNSW model.",
+      "description": "Specify the number of neighbors to search during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "ef.construction",
+      "useInR": true,
+      "rOrderNum": 8
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "NumConnPerNode",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify number of connections for a node during training of HNSW model.",
+      "description": "Specify number of connections for a node during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "numconn.pernode",
+      "useInR": true,
+      "rOrderNum": 9
+    },
+    {
+      "defaultValue": 32,
+      "lowerBound": 1,
+      "upperBound": 1024,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "MaxNumConnPerNode",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify maximum number of connections allowed for a node during training of HNSW model.",
+      "description": "Specify maximum number of connections allowed for a node during training of HNSW model.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "maxnumconn.pernode",
+      "useInR": true,
+      "rOrderNum": 10
+    },
+    {
+      "permittedValues": [
+        "EUCLIDEAN",
+        "COSINE",
+	"DOTPRODUCT"
+      ],
+      "defaultValue": "EUCLIDEAN",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "DistanceMeasure",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the distance measure to be used for distance computation.",
+      "description": "Specify the distance measure to be used for distance computation.",
+      "datatype": "STRING",
+      "allowsLists": false,
+      "rName": "distance.measure",
+      "useInR": true,
+      "rOrderNum": 11
+    },
+    {
+      "lowerBound": 1,
+      "upperBound": 4096,
+      "lowerBoundType": "INCLUSIVE",
+      "upperBoundType": "INCLUSIVE",
+      "allowNaN": false,
+      "name": "EmbeddingSize",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the embedding size of the vectors.",
+      "description": "Specify the embedding size of the vectors.",
+      "datatype": "INTEGER",
+      "allowsLists": false,
+      "rName": "embedding.size",
+      "useInR": true,
+      "rOrderNum": 12
+    },
+    {
+      "permittedValues": [],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "defaultValue": false,
+      "name": "ApplyHeuristics",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify whether to apply heuristics optimizations during training of HNSW model.",
+      "description": "Specify whether to apply heuristics optimizations during training of HNSW model.",
+      "datatype": "BOOLEAN",
+      "allowsLists": false,
+      "rName": "apply.heuristics",
+      "useInR": true,
+      "rOrderNum": 13
+    },
+    {
+      "permittedValues": [
+        "UPDATE",
+        "DELETE"
+      ],
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "AlterOperation",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the alter operation for HNSW model. This argument is required when InputModelTable is provided.",
+      "description": "Specify the alter operation for HNSW model. This argument is required when InputModelTable is provided.",
+      "datatype": "STRING",
+      "allowsLists": true,
+      "rName": "alter.operation",
+      "useInR": true,
+      "rOrderNum": 14
+    },
+    {
+      "permittedValues": [
+        "RECONSTRUCTION",
+        "DELETENODE"
+      ],
+      "defaultValue": "RECONSTRUCTION",
+      "isOutputColumn": false,
+      "matchLengthOfArgument": "",
+      "allowPadding": false,
+      "name": "DeleteMethod",
+      "alternateNames": [],
+      "isRequired": false,
+      "rDescription": "Specify the method for delete operation.",
+      "description": "Specify the method for delete operation.",
+      "datatype": "STRING",
+      "allowsLists": true,
+      "rName": "delete.method",
+      "useInR": true,
+      "rOrderNum": 15
+    }
+  ]
+}