OpenAICompletion implements OpenAICompletion More...

Inheritance diagram for Synapse.ML.Services.Openai.OpenAICompletion:

[legend]

Collaboration diagram for Synapse.ML.Services.Openai.OpenAICompletion:

[legend]

Public Member Functions
	OpenAICompletion ()
	Creates a OpenAICompletion without any parameters. More...

	OpenAICompletion (string uid)
	Creates a OpenAICompletion with a UID that is used to give the OpenAICompletion a unique ID. More...

OpenAICompletion	SetAADToken (string value)
	Sets value for AADToken More...

OpenAICompletion	SetAADTokenCol (string value)
	Sets value for AADToken column More...

OpenAICompletion	SetCustomAuthHeader (string value)
	Sets value for CustomAuthHeader More...

OpenAICompletion	SetCustomAuthHeaderCol (string value)
	Sets value for CustomAuthHeader column More...

OpenAICompletion	SetApiVersion (string value)
	Sets value for apiVersion More...

OpenAICompletion	SetApiVersionCol (string value)
	Sets value for apiVersion column More...

OpenAICompletion	SetBatchPrompt (string[] value)
	Sets value for batchPrompt More...

OpenAICompletion	SetBatchPromptCol (string value)
	Sets value for batchPrompt column More...

OpenAICompletion	SetBestOf (int value)
	Sets value for bestOf More...

OpenAICompletion	SetBestOfCol (string value)
	Sets value for bestOf column More...

OpenAICompletion	SetCacheLevel (int value)
	Sets value for cacheLevel More...

OpenAICompletion	SetCacheLevelCol (string value)
	Sets value for cacheLevel column More...

OpenAICompletion	SetConcurrency (int value)
	Sets value for concurrency More...

OpenAICompletion	SetConcurrentTimeout (double value)
	Sets value for concurrentTimeout More...

OpenAICompletion	SetDeploymentName (string value)
	Sets value for deploymentName More...

OpenAICompletion	SetDeploymentNameCol (string value)
	Sets value for deploymentName column More...

OpenAICompletion	SetEcho (bool value)
	Sets value for echo More...

OpenAICompletion	SetEchoCol (string value)
	Sets value for echo column More...

OpenAICompletion	SetErrorCol (string value)
	Sets value for errorCol More...

OpenAICompletion	SetFrequencyPenalty (double value)
	Sets value for frequencyPenalty More...

OpenAICompletion	SetFrequencyPenaltyCol (string value)
	Sets value for frequencyPenalty column More...

OpenAICompletion	SetHandler (object value)
	Sets value for handler More...

OpenAICompletion	SetLogProbs (int value)
	Sets value for logProbs More...

OpenAICompletion	SetLogProbsCol (string value)
	Sets value for logProbs column More...

OpenAICompletion	SetMaxTokens (int value)
	Sets value for maxTokens More...

OpenAICompletion	SetMaxTokensCol (string value)
	Sets value for maxTokens column More...

OpenAICompletion	SetN (int value)
	Sets value for n More...

OpenAICompletion	SetNCol (string value)
	Sets value for n column More...

OpenAICompletion	SetOutputCol (string value)
	Sets value for outputCol More...

OpenAICompletion	SetPresencePenalty (double value)
	Sets value for presencePenalty More...

OpenAICompletion	SetPresencePenaltyCol (string value)
	Sets value for presencePenalty column More...

OpenAICompletion	SetPrompt (string value)
	Sets value for prompt More...

OpenAICompletion	SetPromptCol (string value)
	Sets value for prompt column More...

OpenAICompletion	SetStop (string value)
	Sets value for stop More...

OpenAICompletion	SetStopCol (string value)
	Sets value for stop column More...

OpenAICompletion	SetSubscriptionKey (string value)
	Sets value for subscriptionKey More...

OpenAICompletion	SetSubscriptionKeyCol (string value)
	Sets value for subscriptionKey column More...

OpenAICompletion	SetTemperature (double value)
	Sets value for temperature More...

OpenAICompletion	SetTemperatureCol (string value)
	Sets value for temperature column More...

OpenAICompletion	SetTimeout (double value)
	Sets value for timeout More...

OpenAICompletion	SetTopP (double value)
	Sets value for topP More...

OpenAICompletion	SetTopPCol (string value)
	Sets value for topP column More...

OpenAICompletion	SetUrl (string value)
	Sets value for url More...

OpenAICompletion	SetUser (string value)
	Sets value for user More...

OpenAICompletion	SetUserCol (string value)
	Sets value for user column More...

string	GetAADToken ()
	Gets AADToken value More...

string	GetCustomAuthHeader ()
	Gets CustomAuthHeader value More...

string	GetApiVersion ()
	Gets apiVersion value More...

string[]	GetBatchPrompt ()
	Gets batchPrompt value More...

int	GetBestOf ()
	Gets bestOf value More...

int	GetCacheLevel ()
	Gets cacheLevel value More...

int	GetConcurrency ()
	Gets concurrency value More...

double	GetConcurrentTimeout ()
	Gets concurrentTimeout value More...

string	GetDeploymentName ()
	Gets deploymentName value More...

bool	GetEcho ()
	Gets echo value More...

string	GetErrorCol ()
	Gets errorCol value More...

double	GetFrequencyPenalty ()
	Gets frequencyPenalty value More...

object	GetHandler ()
	Gets handler value More...

int	GetLogProbs ()
	Gets logProbs value More...

int	GetMaxTokens ()
	Gets maxTokens value More...

int	GetN ()
	Gets n value More...

string	GetOutputCol ()
	Gets outputCol value More...

double	GetPresencePenalty ()
	Gets presencePenalty value More...

string	GetPrompt ()
	Gets prompt value More...

string	GetStop ()
	Gets stop value More...

string	GetSubscriptionKey ()
	Gets subscriptionKey value More...

double	GetTemperature ()
	Gets temperature value More...

double	GetTimeout ()
	Gets timeout value More...

double	GetTopP ()
	Gets topP value More...

string	GetUrl ()
	Gets url value More...

string	GetUser ()
	Gets user value More...

void	Save (string path)
	Saves the object so that it can be loaded later using Load. Note that these objects can be shared with Scala by Loading or Saving in Scala. More...

JavaMLWriter	Write ()
	Returns a JavaMLWriter instance for this ML instance.

JavaMLReader< OpenAICompletion >	Read ()
	Get the corresponding JavaMLReader instance. More...

OpenAICompletion	SetCustomServiceName (string value)
	Sets value for service name More...

OpenAICompletion	SetEndpoint (string value)
	Sets value for endpoint More...

Static Public Member Functions
static OpenAICompletion	Load (string path)
	Loads the OpenAICompletion that was previously saved using Save(string). More...

Detailed Description

OpenAICompletion implements OpenAICompletion

Constructor & Destructor Documentation

◆ OpenAICompletion() [1/2]

Synapse.ML.Services.Openai.OpenAICompletion.OpenAICompletion ( )

inline

Creates a OpenAICompletion without any parameters.

◆ OpenAICompletion() [2/2]

Synapse.ML.Services.Openai.OpenAICompletion.OpenAICompletion ( string uid )

inline

Creates a OpenAICompletion with a UID that is used to give the OpenAICompletion a unique ID.

Parameters

uid	An immutable unique ID for the object and its derivatives.

Member Function Documentation

◆ GetAADToken()

string Synapse.ML.Services.Openai.OpenAICompletion.GetAADToken ( )

Gets AADToken value

Returns: AADToken: AAD Token used for authentication

◆ GetApiVersion()

string Synapse.ML.Services.Openai.OpenAICompletion.GetApiVersion ( )

Gets apiVersion value

Returns: apiVersion: version of the api

◆ GetBatchPrompt()

string [] Synapse.ML.Services.Openai.OpenAICompletion.GetBatchPrompt ( )

Gets batchPrompt value

Returns: batchPrompt: Sequence of prompts to complete

◆ GetBestOf()

int Synapse.ML.Services.Openai.OpenAICompletion.GetBestOf ( )

Gets bestOf value

Returns: bestOf: How many generations to create server side, and display only the best. Will not stream intermediate progress if best_of > 1. Has maximum value of 128.

◆ GetCacheLevel()

int Synapse.ML.Services.Openai.OpenAICompletion.GetCacheLevel ( )

Gets cacheLevel value

Returns: cacheLevel: can be used to disable any server-side caching, 0=no cache, 1=prompt prefix enabled, 2=full cache

◆ GetConcurrency()

int Synapse.ML.Services.Openai.OpenAICompletion.GetConcurrency ( )

Gets concurrency value

Returns: concurrency: max number of concurrent calls

◆ GetConcurrentTimeout()

double Synapse.ML.Services.Openai.OpenAICompletion.GetConcurrentTimeout ( )

Gets concurrentTimeout value

Returns: concurrentTimeout: max number seconds to wait on futures if concurrency >= 1

◆ GetCustomAuthHeader()

string Synapse.ML.Services.Openai.OpenAICompletion.GetCustomAuthHeader ( )

Gets CustomAuthHeader value

Returns: CustomAuthHeader: A Custom Value for Authorization Header

◆ GetDeploymentName()

string Synapse.ML.Services.Openai.OpenAICompletion.GetDeploymentName ( )

Gets deploymentName value

Returns: deploymentName: The name of the deployment

◆ GetEcho()

bool Synapse.ML.Services.Openai.OpenAICompletion.GetEcho ( )

Gets echo value

Returns: echo: Echo back the prompt in addition to the completion

◆ GetErrorCol()

string Synapse.ML.Services.Openai.OpenAICompletion.GetErrorCol ( )

Gets errorCol value

Returns: errorCol: column to hold http errors

◆ GetFrequencyPenalty()

double Synapse.ML.Services.Openai.OpenAICompletion.GetFrequencyPenalty ( )

Gets frequencyPenalty value

Returns: frequencyPenalty: How much to penalize new tokens based on whether they appear in the text so far. Increases the likelihood of the model to talk about new topics.

◆ GetHandler()

object Synapse.ML.Services.Openai.OpenAICompletion.GetHandler ( )

Gets handler value

Returns: handler: Which strategy to use when handling requests

◆ GetLogProbs()

int Synapse.ML.Services.Openai.OpenAICompletion.GetLogProbs ( )

Gets logProbs value

Returns: logProbs: Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. So for example, if logprobs is 10, the API will return a list of the 10 most likely tokens. If logprobs is 0, only the chosen tokens will have logprobs returned. Minimum of 0 and maximum of 100 allowed.

◆ GetMaxTokens()

int Synapse.ML.Services.Openai.OpenAICompletion.GetMaxTokens ( )

Gets maxTokens value

Returns: maxTokens: The maximum number of tokens to generate. Has minimum of 0.

◆ GetN()

int Synapse.ML.Services.Openai.OpenAICompletion.GetN ( )

Gets n value

Returns: n: How many snippets to generate for each prompt. Minimum of 1 and maximum of 128 allowed.

◆ GetOutputCol()

string Synapse.ML.Services.Openai.OpenAICompletion.GetOutputCol ( )

Gets outputCol value

Returns: outputCol: The name of the output column

◆ GetPresencePenalty()

double Synapse.ML.Services.Openai.OpenAICompletion.GetPresencePenalty ( )

Gets presencePenalty value

Returns: presencePenalty: How much to penalize new tokens based on their existing frequency in the text so far. Decreases the likelihood of the model to repeat the same line verbatim. Has minimum of -2 and maximum of 2.

◆ GetPrompt()

string Synapse.ML.Services.Openai.OpenAICompletion.GetPrompt ( )

Gets prompt value

Returns: prompt: The text to complete

◆ GetStop()

string Synapse.ML.Services.Openai.OpenAICompletion.GetStop ( )

Gets stop value

Returns: stop: A sequence which indicates the end of the current document.

◆ GetSubscriptionKey()

string Synapse.ML.Services.Openai.OpenAICompletion.GetSubscriptionKey ( )

Gets subscriptionKey value

Returns: subscriptionKey: the API key to use

◆ GetTemperature()

double Synapse.ML.Services.Openai.OpenAICompletion.GetTemperature ( )

Gets temperature value

Returns: temperature: What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend using this or top_p but not both. Minimum of 0 and maximum of 2 allowed.

◆ GetTimeout()

double Synapse.ML.Services.Openai.OpenAICompletion.GetTimeout ( )

Gets timeout value

Returns: timeout: number of seconds to wait before closing the connection

◆ GetTopP()

double Synapse.ML.Services.Openai.OpenAICompletion.GetTopP ( )

Gets topP value

Returns: topP: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10 percent probability mass are considered. We generally recommend using this or temperature but not both. Minimum of 0 and maximum of 1 allowed.

◆ GetUrl()

string Synapse.ML.Services.Openai.OpenAICompletion.GetUrl ( )

Gets url value

Returns: url: Url of the service

◆ GetUser()

string Synapse.ML.Services.Openai.OpenAICompletion.GetUser ( )

Gets user value

Returns: user: The ID of the end-user, for use in tracking and rate-limiting.

◆ Load()

static OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.Load ( string path )

static

Loads the OpenAICompletion that was previously saved using Save(string).

Parameters

path	The path the previous OpenAICompletion was saved to

Returns: New OpenAICompletion object, loaded from path.

◆ Read()

JavaMLReader<OpenAICompletion> Synapse.ML.Services.Openai.OpenAICompletion.Read ( )

Get the corresponding JavaMLReader instance.

Returns: an JavaMLReader<OpenAICompletion> instance for this ML instance.

◆ Save()

void Synapse.ML.Services.Openai.OpenAICompletion.Save ( string path )

Saves the object so that it can be loaded later using Load. Note that these objects can be shared with Scala by Loading or Saving in Scala.

Parameters

path	The path to save the object to

◆ SetAADToken()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetAADToken ( string value )

Sets value for AADToken

Parameters

value AAD Token used for authentication

Returns: New OpenAICompletion object

◆ SetAADTokenCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetAADTokenCol ( string value )

Sets value for AADToken column

Parameters

value AAD Token used for authentication

Returns: New OpenAICompletion object

◆ SetApiVersion()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetApiVersion ( string value )

Sets value for apiVersion

Parameters

value version of the api

Returns: New OpenAICompletion object

◆ SetApiVersionCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetApiVersionCol ( string value )

Sets value for apiVersion column

Parameters

value version of the api

Returns: New OpenAICompletion object

◆ SetBatchPrompt()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetBatchPrompt ( string[] value )

Sets value for batchPrompt

Parameters

value Sequence of prompts to complete

Returns: New OpenAICompletion object

◆ SetBatchPromptCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetBatchPromptCol ( string value )

Sets value for batchPrompt column

Parameters

value Sequence of prompts to complete

Returns: New OpenAICompletion object

◆ SetBestOf()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetBestOf ( int value )

Sets value for bestOf

Parameters

value How many generations to create server side, and display only the best. Will not stream intermediate progress if best_of > 1. Has maximum value of 128.

Returns: New OpenAICompletion object

◆ SetBestOfCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetBestOfCol ( string value )

Sets value for bestOf column

Parameters

value How many generations to create server side, and display only the best. Will not stream intermediate progress if best_of > 1. Has maximum value of 128.

Returns: New OpenAICompletion object

◆ SetCacheLevel()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetCacheLevel ( int value )

Sets value for cacheLevel

Parameters

value can be used to disable any server-side caching, 0=no cache, 1=prompt prefix enabled, 2=full cache

Returns: New OpenAICompletion object

◆ SetCacheLevelCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetCacheLevelCol ( string value )

Sets value for cacheLevel column

Parameters

value can be used to disable any server-side caching, 0=no cache, 1=prompt prefix enabled, 2=full cache

Returns: New OpenAICompletion object

◆ SetConcurrency()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetConcurrency ( int value )

Sets value for concurrency

Parameters

value max number of concurrent calls

Returns: New OpenAICompletion object

◆ SetConcurrentTimeout()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetConcurrentTimeout ( double value )

Sets value for concurrentTimeout

Parameters

value max number seconds to wait on futures if concurrency >= 1

Returns: New OpenAICompletion object

◆ SetCustomAuthHeader()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetCustomAuthHeader ( string value )

Sets value for CustomAuthHeader

Parameters

value A Custom Value for Authorization Header

Returns: New OpenAICompletion object

◆ SetCustomAuthHeaderCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetCustomAuthHeaderCol ( string value )

Sets value for CustomAuthHeader column

Parameters

value A Custom Value for Authorization Header

Returns: New OpenAICompletion object

◆ SetCustomServiceName()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetCustomServiceName ( string value )

Sets value for service name

Parameters

value Service name of the cognitive service if it's custom domain

Returns: New OpenAICompletion object

◆ SetDeploymentName()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetDeploymentName ( string value )

Sets value for deploymentName

Parameters

value The name of the deployment

Returns: New OpenAICompletion object

◆ SetDeploymentNameCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetDeploymentNameCol ( string value )

Sets value for deploymentName column

Parameters

value The name of the deployment

Returns: New OpenAICompletion object

◆ SetEcho()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetEcho ( bool value )

Sets value for echo

Parameters

value Echo back the prompt in addition to the completion

Returns: New OpenAICompletion object

◆ SetEchoCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetEchoCol ( string value )

Sets value for echo column

Parameters

value Echo back the prompt in addition to the completion

Returns: New OpenAICompletion object

◆ SetEndpoint()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetEndpoint ( string value )

Sets value for endpoint

Parameters

value Endpoint of the cognitive service

Returns: New OpenAICompletion object

◆ SetErrorCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetErrorCol ( string value )

Sets value for errorCol

Parameters

value column to hold http errors

Returns: New OpenAICompletion object

◆ SetFrequencyPenalty()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetFrequencyPenalty ( double value )

Sets value for frequencyPenalty

Parameters

value How much to penalize new tokens based on whether they appear in the text so far. Increases the likelihood of the model to talk about new topics.

Returns: New OpenAICompletion object

◆ SetFrequencyPenaltyCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetFrequencyPenaltyCol ( string value )

Sets value for frequencyPenalty column

Parameters

value How much to penalize new tokens based on whether they appear in the text so far. Increases the likelihood of the model to talk about new topics.

Returns: New OpenAICompletion object

◆ SetHandler()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetHandler ( object value )

Sets value for handler

Parameters

value Which strategy to use when handling requests

Returns: New OpenAICompletion object

◆ SetLogProbs()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetLogProbs ( int value )

Sets value for logProbs

Parameters

value Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. So for example, if logprobs is 10, the API will return a list of the 10 most likely tokens. If logprobs is 0, only the chosen tokens will have logprobs returned. Minimum of 0 and maximum of 100 allowed.

Returns: New OpenAICompletion object

◆ SetLogProbsCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetLogProbsCol ( string value )

Sets value for logProbs column

Parameters

value Include the log probabilities on the logprobs most likely tokens, as well the chosen tokens. So for example, if logprobs is 10, the API will return a list of the 10 most likely tokens. If logprobs is 0, only the chosen tokens will have logprobs returned. Minimum of 0 and maximum of 100 allowed.

Returns: New OpenAICompletion object

◆ SetMaxTokens()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetMaxTokens ( int value )

Sets value for maxTokens

Parameters

value The maximum number of tokens to generate. Has minimum of 0.

Returns: New OpenAICompletion object

◆ SetMaxTokensCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetMaxTokensCol ( string value )

Sets value for maxTokens column

Parameters

value The maximum number of tokens to generate. Has minimum of 0.

Returns: New OpenAICompletion object

◆ SetN()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetN ( int value )

Sets value for n

Parameters

value How many snippets to generate for each prompt. Minimum of 1 and maximum of 128 allowed.

Returns: New OpenAICompletion object

◆ SetNCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetNCol ( string value )

Sets value for n column

Parameters

value How many snippets to generate for each prompt. Minimum of 1 and maximum of 128 allowed.

Returns: New OpenAICompletion object

◆ SetOutputCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetOutputCol ( string value )

Sets value for outputCol

Parameters

value The name of the output column

Returns: New OpenAICompletion object

◆ SetPresencePenalty()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetPresencePenalty ( double value )

Sets value for presencePenalty

Parameters

value How much to penalize new tokens based on their existing frequency in the text so far. Decreases the likelihood of the model to repeat the same line verbatim. Has minimum of -2 and maximum of 2.

Returns: New OpenAICompletion object

◆ SetPresencePenaltyCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetPresencePenaltyCol ( string value )

Sets value for presencePenalty column

Parameters

value How much to penalize new tokens based on their existing frequency in the text so far. Decreases the likelihood of the model to repeat the same line verbatim. Has minimum of -2 and maximum of 2.

Returns: New OpenAICompletion object

◆ SetPrompt()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetPrompt ( string value )

Sets value for prompt

Parameters

value The text to complete

Returns: New OpenAICompletion object

◆ SetPromptCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetPromptCol ( string value )

Sets value for prompt column

Parameters

value The text to complete

Returns: New OpenAICompletion object

◆ SetStop()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetStop ( string value )

Sets value for stop

Parameters

value A sequence which indicates the end of the current document.

Returns: New OpenAICompletion object

◆ SetStopCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetStopCol ( string value )

Sets value for stop column

Parameters

value A sequence which indicates the end of the current document.

Returns: New OpenAICompletion object

◆ SetSubscriptionKey()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetSubscriptionKey ( string value )

Sets value for subscriptionKey

Parameters

value the API key to use

Returns: New OpenAICompletion object

◆ SetSubscriptionKeyCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetSubscriptionKeyCol ( string value )

Sets value for subscriptionKey column

Parameters

value the API key to use

Returns: New OpenAICompletion object

◆ SetTemperature()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetTemperature ( double value )

Sets value for temperature

Parameters

value What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend using this or top_p but not both. Minimum of 0 and maximum of 2 allowed.

Returns: New OpenAICompletion object

◆ SetTemperatureCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetTemperatureCol ( string value )

Sets value for temperature column

Parameters

value What sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend using this or top_p but not both. Minimum of 0 and maximum of 2 allowed.

Returns: New OpenAICompletion object

◆ SetTimeout()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetTimeout ( double value )

Sets value for timeout

Parameters

value number of seconds to wait before closing the connection

Returns: New OpenAICompletion object

◆ SetTopP()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetTopP ( double value )

Sets value for topP

Parameters

value An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10 percent probability mass are considered. We generally recommend using this or temperature but not both. Minimum of 0 and maximum of 1 allowed.

Returns: New OpenAICompletion object

◆ SetTopPCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetTopPCol ( string value )

Sets value for topP column

Parameters

value An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10 percent probability mass are considered. We generally recommend using this or temperature but not both. Minimum of 0 and maximum of 1 allowed.

Returns: New OpenAICompletion object

◆ SetUrl()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetUrl ( string value )

Sets value for url

Parameters

value Url of the service

Returns: New OpenAICompletion object

◆ SetUser()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetUser ( string value )

Sets value for user

Parameters

value The ID of the end-user, for use in tracking and rate-limiting.

Returns: New OpenAICompletion object

◆ SetUserCol()

OpenAICompletion Synapse.ML.Services.Openai.OpenAICompletion.SetUserCol ( string value )

Sets value for user column

Parameters

value The ID of the end-user, for use in tracking and rate-limiting.

Returns: New OpenAICompletion object

The documentation for this class was generated from the following file:

synapse/ml/services/openai/OpenAICompletion.cs

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ OpenAICompletion() [1/2]

◆ OpenAICompletion() [2/2]

Member Function Documentation

◆ GetAADToken()

◆ GetApiVersion()

◆ GetBatchPrompt()

◆ GetBestOf()

◆ GetCacheLevel()

◆ GetConcurrency()

◆ GetConcurrentTimeout()

◆ GetCustomAuthHeader()

◆ GetDeploymentName()

◆ GetEcho()

◆ GetErrorCol()

◆ GetFrequencyPenalty()

◆ GetHandler()

◆ GetLogProbs()

◆ GetMaxTokens()

◆ GetN()

◆ GetOutputCol()

◆ GetPresencePenalty()

◆ GetPrompt()

◆ GetStop()

◆ GetSubscriptionKey()

◆ GetTemperature()

◆ GetTimeout()

◆ GetTopP()

◆ GetUrl()

◆ GetUser()

◆ Load()

◆ Read()

◆ Save()

◆ SetAADToken()

◆ SetAADTokenCol()

◆ SetApiVersion()

◆ SetApiVersionCol()

◆ SetBatchPrompt()

◆ SetBatchPromptCol()

◆ SetBestOf()

◆ SetBestOfCol()

◆ SetCacheLevel()

◆ SetCacheLevelCol()

◆ SetConcurrency()

◆ SetConcurrentTimeout()

◆ SetCustomAuthHeader()

◆ SetCustomAuthHeaderCol()

◆ SetCustomServiceName()

◆ SetDeploymentName()

◆ SetDeploymentNameCol()

◆ SetEcho()

◆ SetEchoCol()

◆ SetEndpoint()

◆ SetErrorCol()

◆ SetFrequencyPenalty()

◆ SetFrequencyPenaltyCol()

◆ SetHandler()

◆ SetLogProbs()

◆ SetLogProbsCol()

◆ SetMaxTokens()

◆ SetMaxTokensCol()

◆ SetN()

◆ SetNCol()

◆ SetOutputCol()

◆ SetPresencePenalty()

◆ SetPresencePenaltyCol()

◆ SetPrompt()

◆ SetPromptCol()

◆ SetStop()

◆ SetStopCol()

◆ SetSubscriptionKey()

◆ SetSubscriptionKeyCol()

◆ SetTemperature()

◆ SetTemperatureCol()

◆ SetTimeout()

◆ SetTopP()

◆ SetTopPCol()