PromptExecutionSettings Class

public static final int DEFAULT_BEST_OF

The default for getBestOf() if best_of is not provided. Defaults to 1

public static final double DEFAULT_FREQUENCY_PENALTY

The default for getFrequencyPenalty() if Builder#withFrequencyPenalty(double) frequency_penalty} is not provided. Defaults to 0.0

public static final int DEFAULT_MAX_TOKENS

The default for getMaxTokens() if max_tokens is not provided. Defaults to 256

public static final double DEFAULT_PRESENCE_PENALTY

The default for getPresencePenalty() if presence_penalty is not provided. Defaults to 0.0

public static final int DEFAULT_RESULTS_PER_PROMPT

The default for getResultsPerPrompt() if results per prompt (n) is not provided. Defaults to 1

public static final String DEFAULT_SERVICE_ID

The default for getServiceId() if a service id is not provided. Defaults to "default"

public static final double DEFAULT_TEMPERATURE

The default for getTemperature() if temperature is not provided. Defaults to 1.0

public static final double DEFAULT_TOP_P

The default for getTopP() if top_p is not provided. Defaults to 1.0

public PromptExecutionSettings(String serviceId, String modelId, Double temperature, Double topP, Double presencePenalty, Double frequencyPenalty, Integer maxTokens, Integer resultsPerPrompt, Integer bestOf, String user, List stopSequences, Map tokenSelectionBiases, ResponseFormat responseFormat)

Create a new instance of PromptExecutionSettings.

Parameters:

public static PromptExecutionSettings.Builder builder()

Create a new builder for PromptExecutionSettings.

Returns:

public boolean equals(Object obj)

Overrides:

PromptExecutionSettings.equals(Object obj)

Parameters:

public int getBestOf()

The log probability threshold for a result to be considered.

Returns:

public double getFrequencyPenalty()

Frequency penalty encourages the model to avoid repeating the same token in the output. A higher value means that the model will be less likely to repeat a token.

Returns:

public int getMaxTokens()

The maximum number of tokens to generate in the output.

Returns:

public String getModelId()

Get the id of the model to use for prompt execution.

Returns:

public double getPresencePenalty()

Presence penalty encourages the model to use a more or less diverse range of tokens in the output. A higher value means that the model will try to use a greater variety of tokens in the output.

Returns:

public ResponseFormat getResponseFormat()

The response format to use for prompt execution. Currently this only applies to chat completions.

Returns:

public int getResultsPerPrompt()

The number of results to generate for each prompt.

Returns:

public String getServiceId()

Get the id of the AI service to use for prompt execution.

Returns:

public List getStopSequences()

The stop sequences to use for prompt execution.

Returns:

public double getTemperature()

The temperature setting controls the randomness of the output. Lower values produce more deterministic outputs, while higher values produce more random outputs.

Returns:

public Map getTokenSelectionBiases()

The token selection biases to use for prompt execution. The key is the token id from the tokenizer, and the value is the bias. A negative bias will make the model less likely to use the token, and a positive bias will make the model more likely to use the token.

Returns:

public double getTopP()

The topP setting controls how many different words or phrases are considered to predict the next token. The value is a probability threshold, and the model considers the most likely tokens whose cumulative probability mass is greater than the threshold. For example, if the value is 0.1, the model considers only the tokens that make up the top 10% of the cumulative probability mass.

Returns:

public String getUser()

The user to associate with the prompt execution.

Returns:

public int hashCode()

Overrides:

PromptExecutionSettings.hashCode()