Source code for synapse.ml.services.openai.OpenAIEmbedding

# Copyright (C) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License. See LICENSE in project root for information.


import sys
if sys.version >= '3':
    basestring = str

from pyspark import SparkContext, SQLContext
from pyspark.sql import DataFrame
from pyspark.ml.param.shared import *
from pyspark import keyword_only
from pyspark.ml.util import JavaMLReadable, JavaMLWritable
from synapse.ml.core.platform import running_on_synapse_internal
from synapse.ml.core.serialize.java_params_patch import *
from pyspark.ml.wrapper import JavaTransformer, JavaEstimator, JavaModel
from pyspark.ml.evaluation import JavaEvaluator
from pyspark.ml.common import inherit_doc
from synapse.ml.core.schema.Utils import *
from pyspark.ml.param import TypeConverters
from synapse.ml.core.schema.TypeConversionUtils import generateTypeConverter, complexTypeConverter


[docs]@inherit_doc class OpenAIEmbedding(ComplexParamsMixin, JavaMLReadable, JavaMLWritable, JavaTransformer): """ Args: AADToken (object): AAD Token used for authentication CustomAuthHeader (object): A Custom Value for Authorization Header apiVersion (object): version of the api concurrency (int): max number of concurrent calls concurrentTimeout (float): max number seconds to wait on futures if concurrency >= 1 customHeaders (object): Map of Custom Header Key-Value Tuples. customUrlRoot (str): The custom URL root for the service. This will not append OpenAI specific model path completions (i.e. /chat/completions) to the URL. deploymentName (object): The name of the deployment dimensions (object): Number of dimensions for output embeddings. errorCol (str): column to hold http errors handler (object): Which strategy to use when handling requests outputCol (str): The name of the output column subscriptionKey (object): the API key to use text (object): Input text to get embeddings for. timeout (float): number of seconds to wait before closing the connection url (str): Url of the service user (object): The ID of the end-user, for use in tracking and rate-limiting. """ AADToken = Param(Params._dummy(), "AADToken", "ServiceParam: AAD Token used for authentication") CustomAuthHeader = Param(Params._dummy(), "CustomAuthHeader", "ServiceParam: A Custom Value for Authorization Header") apiVersion = Param(Params._dummy(), "apiVersion", "ServiceParam: version of the api") concurrency = Param(Params._dummy(), "concurrency", "max number of concurrent calls", typeConverter=TypeConverters.toInt) concurrentTimeout = Param(Params._dummy(), "concurrentTimeout", "max number seconds to wait on futures if concurrency >= 1", typeConverter=TypeConverters.toFloat) customHeaders = Param(Params._dummy(), "customHeaders", "ServiceParam: Map of Custom Header Key-Value Tuples.") customUrlRoot = Param(Params._dummy(), "customUrlRoot", "The custom URL root for the service. This will not append OpenAI specific model path completions (i.e. /chat/completions) to the URL.", typeConverter=TypeConverters.toString) deploymentName = Param(Params._dummy(), "deploymentName", "ServiceParam: The name of the deployment") dimensions = Param(Params._dummy(), "dimensions", "ServiceParam: Number of dimensions for output embeddings.") errorCol = Param(Params._dummy(), "errorCol", "column to hold http errors", typeConverter=TypeConverters.toString) handler = Param(Params._dummy(), "handler", "Which strategy to use when handling requests") outputCol = Param(Params._dummy(), "outputCol", "The name of the output column", typeConverter=TypeConverters.toString) subscriptionKey = Param(Params._dummy(), "subscriptionKey", "ServiceParam: the API key to use") text = Param(Params._dummy(), "text", "ServiceParam: Input text to get embeddings for.") timeout = Param(Params._dummy(), "timeout", "number of seconds to wait before closing the connection", typeConverter=TypeConverters.toFloat) url = Param(Params._dummy(), "url", "Url of the service", typeConverter=TypeConverters.toString) user = Param(Params._dummy(), "user", "ServiceParam: The ID of the end-user, for use in tracking and rate-limiting.") @keyword_only def __init__( self, java_obj=None, AADToken=None, AADTokenCol=None, CustomAuthHeader=None, CustomAuthHeaderCol=None, apiVersion=None, apiVersionCol=None, concurrency=1, concurrentTimeout=None, customHeaders=None, customHeadersCol=None, customUrlRoot=None, deploymentName=None, deploymentNameCol=None, dimensions=None, dimensionsCol=None, errorCol="OpenAIEmbedding_531aa802682f_error", handler=None, outputCol="OpenAIEmbedding_531aa802682f_output", subscriptionKey=None, subscriptionKeyCol=None, text=None, textCol=None, timeout=360.0, url=None, user=None, userCol=None ): super(OpenAIEmbedding, self).__init__() if java_obj is None: self._java_obj = self._new_java_obj("com.microsoft.azure.synapse.ml.services.openai.OpenAIEmbedding", self.uid) else: self._java_obj = java_obj self._setDefault(concurrency=1) self._setDefault(errorCol="OpenAIEmbedding_531aa802682f_error") self._setDefault(outputCol="OpenAIEmbedding_531aa802682f_output") self._setDefault(timeout=360.0) if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs if java_obj is None: for k,v in kwargs.items(): if v is not None: getattr(self, "set" + k[0].upper() + k[1:])(v)
[docs] @keyword_only def setParams( self, AADToken=None, AADTokenCol=None, CustomAuthHeader=None, CustomAuthHeaderCol=None, apiVersion=None, apiVersionCol=None, concurrency=1, concurrentTimeout=None, customHeaders=None, customHeadersCol=None, customUrlRoot=None, deploymentName=None, deploymentNameCol=None, dimensions=None, dimensionsCol=None, errorCol="OpenAIEmbedding_531aa802682f_error", handler=None, outputCol="OpenAIEmbedding_531aa802682f_output", subscriptionKey=None, subscriptionKeyCol=None, text=None, textCol=None, timeout=360.0, url=None, user=None, userCol=None ): """ Set the (keyword only) parameters """ if hasattr(self, "_input_kwargs"): kwargs = self._input_kwargs else: kwargs = self.__init__._input_kwargs return self._set(**kwargs)
[docs] @classmethod def read(cls): """ Returns an MLReader instance for this class. """ return JavaMMLReader(cls)
[docs] @staticmethod def getJavaPackage(): """ Returns package name String. """ return "com.microsoft.azure.synapse.ml.services.openai.OpenAIEmbedding"
@staticmethod def _from_java(java_stage): module_name=OpenAIEmbedding.__module__ module_name=module_name.rsplit(".", 1)[0] + ".OpenAIEmbedding" return from_java(java_stage, module_name)
[docs] def setAADToken(self, value): """ Args: AADToken: AAD Token used for authentication """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setAADToken(value) return self
[docs] def setAADTokenCol(self, value): """ Args: AADToken: AAD Token used for authentication """ self._java_obj = self._java_obj.setAADTokenCol(value) return self
[docs] def setCustomAuthHeader(self, value): """ Args: CustomAuthHeader: A Custom Value for Authorization Header """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setCustomAuthHeader(value) return self
[docs] def setCustomAuthHeaderCol(self, value): """ Args: CustomAuthHeader: A Custom Value for Authorization Header """ self._java_obj = self._java_obj.setCustomAuthHeaderCol(value) return self
[docs] def setApiVersion(self, value): """ Args: apiVersion: version of the api """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setApiVersion(value) return self
[docs] def setApiVersionCol(self, value): """ Args: apiVersion: version of the api """ self._java_obj = self._java_obj.setApiVersionCol(value) return self
[docs] def setConcurrency(self, value): """ Args: concurrency: max number of concurrent calls """ self._set(concurrency=value) return self
[docs] def setConcurrentTimeout(self, value): """ Args: concurrentTimeout: max number seconds to wait on futures if concurrency >= 1 """ self._set(concurrentTimeout=value) return self
[docs] def setCustomHeaders(self, value): """ Args: customHeaders: Map of Custom Header Key-Value Tuples. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setCustomHeaders(value) return self
[docs] def setCustomHeadersCol(self, value): """ Args: customHeaders: Map of Custom Header Key-Value Tuples. """ self._java_obj = self._java_obj.setCustomHeadersCol(value) return self
[docs] def setCustomUrlRoot(self, value): """ Args: customUrlRoot: The custom URL root for the service. This will not append OpenAI specific model path completions (i.e. /chat/completions) to the URL. """ self._set(customUrlRoot=value) return self
[docs] def setDeploymentName(self, value): """ Args: deploymentName: The name of the deployment """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setDeploymentName(value) return self
[docs] def setDeploymentNameCol(self, value): """ Args: deploymentName: The name of the deployment """ self._java_obj = self._java_obj.setDeploymentNameCol(value) return self
[docs] def setDimensions(self, value): """ Args: dimensions: Number of dimensions for output embeddings. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setDimensions(value) return self
[docs] def setDimensionsCol(self, value): """ Args: dimensions: Number of dimensions for output embeddings. """ self._java_obj = self._java_obj.setDimensionsCol(value) return self
[docs] def setErrorCol(self, value): """ Args: errorCol: column to hold http errors """ self._set(errorCol=value) return self
[docs] def setHandler(self, value): """ Args: handler: Which strategy to use when handling requests """ self._set(handler=value) return self
[docs] def setOutputCol(self, value): """ Args: outputCol: The name of the output column """ self._set(outputCol=value) return self
[docs] def setSubscriptionKey(self, value): """ Args: subscriptionKey: the API key to use """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setSubscriptionKey(value) return self
[docs] def setSubscriptionKeyCol(self, value): """ Args: subscriptionKey: the API key to use """ self._java_obj = self._java_obj.setSubscriptionKeyCol(value) return self
[docs] def setText(self, value): """ Args: text: Input text to get embeddings for. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setText(value) return self
[docs] def setTextCol(self, value): """ Args: text: Input text to get embeddings for. """ self._java_obj = self._java_obj.setTextCol(value) return self
[docs] def setTimeout(self, value): """ Args: timeout: number of seconds to wait before closing the connection """ self._set(timeout=value) return self
[docs] def setUrl(self, value): """ Args: url: Url of the service """ self._set(url=value) return self
[docs] def setUser(self, value): """ Args: user: The ID of the end-user, for use in tracking and rate-limiting. """ if isinstance(value, list): value = SparkContext._active_spark_context._jvm.com.microsoft.azure.synapse.ml.param.ServiceParam.toSeq(value) self._java_obj = self._java_obj.setUser(value) return self
[docs] def setUserCol(self, value): """ Args: user: The ID of the end-user, for use in tracking and rate-limiting. """ self._java_obj = self._java_obj.setUserCol(value) return self
[docs] def getAADToken(self): """ Returns: AADToken: AAD Token used for authentication """ return self._java_obj.getAADToken()
[docs] def getCustomAuthHeader(self): """ Returns: CustomAuthHeader: A Custom Value for Authorization Header """ return self._java_obj.getCustomAuthHeader()
[docs] def getApiVersion(self): """ Returns: apiVersion: version of the api """ return self._java_obj.getApiVersion()
[docs] def getConcurrency(self): """ Returns: concurrency: max number of concurrent calls """ return self.getOrDefault(self.concurrency)
[docs] def getConcurrentTimeout(self): """ Returns: concurrentTimeout: max number seconds to wait on futures if concurrency >= 1 """ return self.getOrDefault(self.concurrentTimeout)
[docs] def getCustomHeaders(self): """ Returns: customHeaders: Map of Custom Header Key-Value Tuples. """ return self._java_obj.getCustomHeaders()
[docs] def getCustomUrlRoot(self): """ Returns: customUrlRoot: The custom URL root for the service. This will not append OpenAI specific model path completions (i.e. /chat/completions) to the URL. """ return self.getOrDefault(self.customUrlRoot)
[docs] def getDeploymentName(self): """ Returns: deploymentName: The name of the deployment """ return self._java_obj.getDeploymentName()
[docs] def getDimensions(self): """ Returns: dimensions: Number of dimensions for output embeddings. """ return self._java_obj.getDimensions()
[docs] def getErrorCol(self): """ Returns: errorCol: column to hold http errors """ return self.getOrDefault(self.errorCol)
[docs] def getHandler(self): """ Returns: handler: Which strategy to use when handling requests """ return self.getOrDefault(self.handler)
[docs] def getOutputCol(self): """ Returns: outputCol: The name of the output column """ return self.getOrDefault(self.outputCol)
[docs] def getSubscriptionKey(self): """ Returns: subscriptionKey: the API key to use """ return self._java_obj.getSubscriptionKey()
[docs] def getText(self): """ Returns: text: Input text to get embeddings for. """ return self._java_obj.getText()
[docs] def getTimeout(self): """ Returns: timeout: number of seconds to wait before closing the connection """ return self.getOrDefault(self.timeout)
[docs] def getUrl(self): """ Returns: url: Url of the service """ return self.getOrDefault(self.url)
[docs] def getUser(self): """ Returns: user: The ID of the end-user, for use in tracking and rate-limiting. """ return self._java_obj.getUser()
[docs] def setCustomServiceName(self, value): self._java_obj = self._java_obj.setCustomServiceName(value) return self
[docs] def setEndpoint(self, value): self._java_obj = self._java_obj.setEndpoint(value) return self
[docs] def setDefaultInternalEndpoint(self, value): self._java_obj = self._java_obj.setDefaultInternalEndpoint(value) return self
def _transform(self, dataset: DataFrame) -> DataFrame: return super()._transform(dataset)