teradataml 20.0.0.4__py3-none-any.whl → 20.0.0.6__py3-none-any.whl

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

@@ -0,0 +1,134 @@
+{
+	  "json_schema_major_version": "1",
+	  "json_schema_minor_version": "1",
+	  "json_content_version": "1",
+	  "function_name": "TD_TextMorph",
+	  "function_version": "1.0",
+	  "function_type": "fastpath",
+	  "function_category": "Text Analysis",
+	  "function_alias_name": "TD_TextMorph",
+	  "function_r_name": "td.textmorph",
+	  "short_description": "This function is used to generate morph of given words in the input dataset.",
+	  "long_description": "This function is used to generate morph of given words in the input dataset.",
+	  "input_tables": [
+	    {
+	      "requiredInputKind": [
+	        "PartitionByAny"
+	      ],
+	      "isOrdered": false,
+	      "partitionByOne": false,
+	      "name": "InputTable",
+	      "alternateNames": [],
+	      "isRequired": true,
+	      "rDescription": "The table that contains the input dataset.",
+	      "description": "The table that contains the input dataset.",
+	      "datatype": "TABLE_ALIAS",
+	      "allowsLists": false,
+	      "rName": "data",
+	      "useInR": true,
+	      "rOrderNum": 1
+	    }
+	  ],
+	  "argument_clauses": [
+	    {
+	      "targetTable": [
+	        "InputTable"
+	      ],
+	      "checkDuplicate": true,
+	      "allowedTypes": [],
+	      "allowedTypeGroups": [
+	        "STRING"
+	      ],
+	      "matchLengthOfArgument": "",
+	      "allowPadding": false,
+	      "name": "WordColumn",
+	      "alternateNames": [],
+	      "isRequired": true,
+	      "rDescription": "Specify the name of the input column that contains words, for which morphs to be generated.",
+	      "description": "Specify the name of the input column that contains words, for which morphs to be generated.",
+	      "datatype": "COLUMNS",
+	      "allowsLists": false,
+	      "rName": "word.column",
+	      "useInR": true,
+	      "rOrderNum": 2
+	    },
+	    {
+	        "permittedValues": [
+            "NOUN",
+            "VERB",
+            "ADV",
+		    "ADJ"
+          ],
+          "isOutputColumn": false,
+		  "matchLengthOfArgument": "",
+          "allowPadding": false,
+          "name": "POS",
+          "alternateNames": [],
+          "isRequired": false,
+          "rDescription": "Specifies the part of speech to output.",
+          "description": "Specifies the part of speech to output.",
+          "datatype": "STRING",
+          "allowsLists": true,
+          "rName": "pos",
+          "useInR": true,
+          "rOrderNum": 3
+	    },
+	    {
+			"defaultValue": false,
+            "name": "SingleOutput",
+            "alternateNames": [],
+            "isRequired": false,
+            "rDescription": " Specify whether to output only one morph for each word. If user specifies 'false', the function outputs all morphs for each word.",
+            "description": " Specify whether to output only one morph for each word. If user specifies 'false', the function outputs all morphs for each word.",
+            "datatype": "BOOLEAN",
+            "allowsLists": false,
+            "rName": "single.output",
+            "useInR": true,
+            "rOrderNum": 4
+	    },
+		{
+			"targetTable": [
+			"InputTable"
+			],
+			"checkDuplicate": true,
+            "allowedTypes": [],
+            "allowedTypeGroups": [
+            "STRING"
+			],
+			"matchLengthOfArgument": "",
+            "allowPadding": false,
+            "name": "POSTagColumn",
+            "alternateNames": [],
+            "isRequired": false,
+            "rDescription": "Specify the name of the input table column that contains the part-of-speech (POS) tags of the words, output by the function TD_POSTagger.",
+            "description": "Specify the name of the input table column that contains the part-of-speech (POS) tags of the words, output by the function TD_POSTagger.",
+            "datatype": "COLUMNS",
+            "allowsLists": false,
+            "rName": "postag.column",
+            "useInR": true,
+            "rOrderNum": 5
+		},
+	    {
+			"targetTable": [
+            "InputTable"
+          ],
+          "checkDuplicate": true,
+          "allowedTypes": [],
+          "allowedTypeGroups": [
+            "ALL"
+          ],
+          "matchLengthOfArgument": "",
+          "allowPadding": false,
+          "name": "Accumulate",
+          "alternateNames": [],
+          "isRequired": false,
+          "rDescription": "Specifies the names of the input columns to copy to the output table.",
+          "description": "Specifies the names of the input columns to copy to the output table.",
+          "datatype": "COLUMNS",
+          "allowsLists": true,
+          "rName": "accumulate",
+          "useInR": true,
+          "rOrderNum": 6		
+	    }
+	  ]
+}

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

@@ -67,6 +67,23 @@
 			"useInR": true,
 			"rOrderNum": 3
 		},
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "EnforceTokenLimit",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to throw an informative error when finding token larger than 64K/32K or silently discard those tokens larger.",
+			"description": "Specifies whether to throw an informative error when finding token larger than 64K/32K or silently discard those tokens larger.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "enforce.token.limit",
+			"useInR": true,
+			"rOrderNum": 4
+		},		
 		{
 			"defaultValue": true,
 			"permittedValues": [],
@@ -82,7 +99,7 @@
 			"allowsLists": false,
 			"rName": "convert.to.lowercase",
 			"useInR": true,
-			"rOrderNum": 4
+			"rOrderNum": 5
 		},
 		{
 			"defaultValue": false,
@@ -99,7 +116,7 @@
 			"allowsLists": false,
 			"rName": "stem.tokens",
 			"useInR": true,
-			"rOrderNum": 5
+			"rOrderNum": 6
 		},
 		{
 			"defaultValue": false,
@@ -116,7 +133,7 @@
 			"allowsLists": false,
 			"rName": "remove.stopwords",
 			"useInR": true,
-			"rOrderNum": 6
+			"rOrderNum": 7
 		},
 		{
 			"targetTable": [
@@ -138,7 +155,7 @@
 			"allowsLists": true,
 			"rName": "accumulate",
 			"useInR": true,
-			"rOrderNum": 7
+			"rOrderNum": 8
 		},
 		{
 			"defaultValue": " \\t\\n\\f\\r",
@@ -154,8 +171,23 @@
 			"allowsLists": false,
 			"rName": "delimiter",
 			"useInR": true,
-			"rOrderNum": 8
+			"rOrderNum": 9
 		},
+		{
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "DelimiterRegex",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies a PCRE regular expression that represents the word delimiter.",
+			"description": "Specifies a PCRE regular expression that represents the word delimiter.",
+			"datatype": "STRING",
+			"allowsLists": false,
+			"rName": "delimiter.regex",
+			"useInR": true,
+			"rOrderNum": 10
+		},		
 		{
 			"defaultValue": "!#$%&()*+,-./:;?@\\^_`{|}~",
 			"isOutputColumn": false,
@@ -170,7 +202,7 @@
 			"allowsLists": false,
 			"rName": "punctuation",
 			"useInR": true,
-			"rOrderNum": 9
+			"rOrderNum": 11
 		},
 		{
 			"defaultValue": "token",
@@ -186,7 +218,80 @@
 			"allowsLists": false,
 			"rName": "token.col.name",
 			"useInR": true,
-			"rOrderNum": 10
-		}
+			"rOrderNum": 12
+		},
+		{
+			"targetTable": [
+				"InputTable"
+			],
+			"checkDuplicate": true,
+			"allowedTypes": [],
+			"allowedTypeGroups": [
+				"INTEGER"
+			],
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "DocIdColumn",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "specifies the name of the column that uniquely identifies a row in the input table.",
+			"description": "specifies the name of the column that uniquely identifies a row in the input table.",
+			"datatype": "COLUMNS",
+			"allowsLists": false,
+			"rName": "doc.id.column",
+			"useInR": true,
+			"rOrderNum": 13
+		},	     
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "ListPositions",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output the positions of a word in list form.",
+			"description": "Specifies whether to output the positions of a word in list form.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "list.positions",
+			"useInR": true,
+			"rOrderNum": 14
+		},
+		{
+			"defaultValue": false,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "TokenFrequency",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output the frequency for each token.",
+			"description": "Specifies whether to output the frequency for each token.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "token.frequency",
+			"useInR": true,
+			"rOrderNum": 15
+		},
+		{
+			"defaultValue": true,
+			"permittedValues": [],
+			"isOutputColumn": false,
+			"matchLengthOfArgument": "",
+			"allowPadding": false,
+			"name": "OutputByWord",
+			"alternateNames": [],
+			"isRequired": false,
+			"rDescription": "Specifies whether to output each token in a separate row or all tokens in one.",
+			"description": "Specifies whether to output each token in a separate row or all tokens in one.",
+			"datatype": "BOOLEAN",
+			"allowsLists": false,
+			"rName": "output.by.word",
+			"useInR": true,
+			"rOrderNum": 16
+		}	
 	]
-}
+}

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

@@ -0,0 +1,328 @@
+{
+  "json_schema_major_version": "1",
+  "json_schema_minor_version": "2",
+  "json_content_version": "1",
+  "function_name": "AI_AnalyzeSentiment",
+  "function_version": "1.0",
+  "function_type": "fastpath",
+  "function_category": "Text Analytics AI",
+  "function_alias_name": "AIAnalyzeSentiment",
+  "function_r_name": "aa.ai_analyzesentiment",
+  "supports_view": false,
+  "short_description": "This function is used to analyze the sentiment of the text in the specified column of a Teradata Table based on the text analysis, the sentiment can be positive, negative, or neutral.",
+  "long_description": "This function is used to analyze the sentiment of the text in the specified column of a Teradata Table based on the text analysis, the sentiment can be positive, negative, or neutral.",
+  "input_tables": [
+    {
+      "isOrdered": false,
+      "partitionByOne": false,
+      "name": "InputTable",
+      "alternateNames": [],
+      "isRequired": true,
+      "rDescription": "Specifies the table containing the input data.",
+      "description": "Specifies the table containing the input data.",
+      "datatype": "TABLE_ALIAS",
+      "allowsLists": false,
+      "rName": "data",
+      "useInR": true,
+      "rOrderNum": 1
+    }
+  ],
+  "argument_clauses": [
+      {
+        "name": "ApiBase",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 2,
+        "allowNaN": false,
+        "description": "Specifies the LLM API base URL for azure.",
+        "rDescription": "Specifies the LLM API base URL for azure.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "api.base",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "ApiKey",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 3,
+        "allowNaN": false,
+        "description": "Specifies the LLM API Key for azure.",
+        "rDescription": "Specifies the LLM API Key for azure.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "api.key",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "ApiVersion",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 4,
+        "allowNaN": false,
+        "description": "Specifies the LLM API version for azure.",
+        "rDescription": "Specifies the LLM API version for azure.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "api.version",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "DeploymentId",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 5,
+        "allowNaN": false,
+        "description": "Specifies the deployment id of the LLM. It takes engine id for azure OpenAI.",
+        "rDescription": "Specifies the deployment id of the LLM. It takes engine id for azure OpenAI.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "deployment.id",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "ModelName",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 6,
+        "allowNaN": false,
+        "description": "Name of the large language model to be used for text analytics tasks.",
+        "rDescription": "Name of the large language model to be used for text analytics tasks.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "model.name",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "ModelArgs",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 7,
+        "allowNaN": false,
+        "description": "JSON string representing the inference parameters for the selected LLM Model.",
+        "rDescription": "JSON string representing the inference parameters for the selected LLM Model.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "model.args",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "ApiType",
+        "alternateNames": [],
+        "isRequired": true,
+        "rOrderNum": 8,
+        "permittedValues": ["azure","aws","gcp","nim"],
+        "allowNaN": false,
+        "description": "Identification of the cloud platform.",
+        "rDescription": "Identification of the cloud platform.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "api.type",
+        "useInR": true,
+        "rFormulaUsage": false,
+        "rDefaultValue": null
+      },
+      {
+        "name": "AccessKey",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 9,
+        "allowNaN": false,
+        "description": "Specifies the AWS Bedrock service access key.",
+        "rDescription": "Specifies the AWS Bedrock service access key.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "access.key",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "SecretKey",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 10,
+        "allowNaN": false,
+        "description": "Specifies the AWS Bedrock service secret key.",
+        "rDescription": "Specifies the AWS Bedrock service secret key.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "secret.key",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "SessionKey",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 11,
+        "allowNaN": false,
+        "description": "Specifies the AWS bedrock service session key.",
+        "rDescription": "Specifies the AWS bedrock service session key.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "session.key",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "Region",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 12,
+        "allowNaN": false,
+        "description": "Specifies the name of the AWS Bedrock service region or Google Cloud service region depending on the api type.",
+        "rDescription": "Specifies the name of the AWS Bedrock service region or Google Cloud service region depending on the api type.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "region",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      
+      {
+        "name": "AccessToken",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 13,
+        "allowNaN": false,
+        "description": "Specifies the session token for google cloud.",
+        "rDescription": "Specifies the session token for google cloud.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "access.token",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "Project",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum": 14,
+        "allowNaN": false,
+        "description": "Specify the name of the gcp project.",
+        "rDescription": "Specify the name of the gcp project.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "project",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "name": "EnableSafety",
+        "alternateNames": [],
+        "isRequired": false,
+        "defaultValue": "TRUE",
+        "rOrderNum": 15,
+        "permittedValues": ["TRUE", "FALSE"],
+        "allowNaN": false,
+        "description": "Specifies if the safety feature needs to be enabled when api_type is gcp.",
+        "rDescription": "Specifies if the safety feature needs to be enabled when api_type is gcp.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "enable.safety",
+        "useInR": true,
+        "rFormulaUsage": false
+      },
+      {
+        "targetTable": [
+          "InputTable"
+        ],
+        "checkDuplicate": true,
+        "allowedTypes": ["VARCHAR"],
+        "allowedTypeGroups": [
+          "VARCHAR"
+        ],
+        "matchLengthOfArgument": "",
+        "allowPadding": false,
+        "name": "TextColumn",
+        "alternateNames": [],
+        "isRequired": true,
+        "rDescription": "Specifies the name of the text column to be used as input.",
+        "description": "Specifies the name of the text column to be used as input.",
+        "datatype": "COLUMNS",
+        "allowsLists": false,
+        "rName": "text.column",
+        "useInR": true,
+        "rFormulaUsage": false,
+        "rOrderNum": 16
+      },
+  
+      {
+        "defaultValue": true,
+        "permittedValues": [
+          "true",
+          "false"
+        ],
+        "isOutputColumn": false,
+        "name": "isDebug",
+        "alternateNames": [],
+        "isRequired": false,
+        "rDescription": "Specify whether error logging is required.",
+        "description": "Specify whether error logging is required.",
+        "datatype": "BOOLEAN",
+        "allowsLists": false,
+        "rName": "isDebug",
+        "useInR": true,
+        "rOrderNum": 17
+      },
+      {
+          "targetTable": [
+            "InputTable"
+          ],
+          "checkDuplicate": true,
+          "allowedTypes": [],
+          "allowedTypeGroups": [
+            "ALL"
+          ],
+          "matchLengthOfArgument": "",
+          "allowPadding": false,
+          "name": "Accumulate",
+          "alternateNames": [],
+          "isRequired": false,
+          "rDescription": "Specifies the input table columns to copy to the output table. By default, the function doesn't copy any input table columns to the output table.",
+          "description": "Specifies the input table columns to copy to the output table. By default, the function doesn't copy any input table columns to the output table.",
+          "datatype": "COLUMNS",
+          "allowsLists": true,
+          "rName": "accumulate",
+          "useInR": true,
+          "rOrderNum": 18
+      },
+      {
+        "name": "AUTHORIZATION",
+        "alternateNames": [],
+        "isRequired": false,
+        "rOrderNum":19,
+        "allowNaN": false,
+        "description": "Specifies the authorization object name containing the credentials, optionally prefixed by the database name.",
+        "rDescription": "Specifies the authorization object name containing the credentials, optionally prefixed by the database name.",
+        "datatype": "STRING",
+        "allowsLists": false,
+        "allowPadding": true,
+        "rName": "authorization",
+        "useInR": true,
+        "rFormulaUsage": false
+      }
+  ]
+}
+
+