Class OpenAIModelConfiguration

Inheritance

object

OpenAIModelConfiguration

ChatGptModelConfiguration

Implements

IEquatable<OpenAIModelConfiguration>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Namespace: DotnetPrompt.LLM.OpenAI

Assembly: DotnetPrompt.LLM.OpenAI.dll

Syntax

public record OpenAIModelConfiguration : IEquatable<OpenAIModelConfiguration>

Fields

| Improve this Doc View Source

Default

Default model configuration

Declaration

public static OpenAIModelConfiguration Default

Field Value

Type	Description
OpenAIModelConfiguration

Properties

| Improve this Doc View Source

CacheLevel

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

Declaration

[JsonPropertyName("cache_level")]
public int? CacheLevel { get; init; }

Property Value

Type	Description
int?

| Improve this Doc View Source

CompletionConfig

Completion configuration.

Declaration

[JsonPropertyName("completion_config")]
public string CompletionConfig { get; init; }

Property Value

Type	Description
string

| Improve this Doc View Source

Echo

Echo back the prompt in addition to the completion.

Declaration

[JsonPropertyName("echo")]
public bool? Echo { get; init; }

Property Value

Type	Description
bool?

| Improve this Doc View Source

FrequencyPenalty

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

Declaration

[JsonPropertyName("frequency_penalty")]
public float? FrequencyPenalty { get; init; }

Property Value

Type	Description
float?

| Improve this Doc View Source

GenerationSampleCount

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.

Declaration

[JsonPropertyName("best_of")]
public int? GenerationSampleCount { get; init; }

Property Value

Type	Description
int?

| Improve this Doc View Source

LogitBias

Defaults to null. Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this tokenizer tool (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. As an example, you can pass {"50256" : -100} to prevent the <|endoftext|> token from being generated.

Declaration

[JsonPropertyName("logit_bias")]
public IDictionary<string, int> LogitBias { get; init; }

Property Value

Type	Description
IDictionary<string, int>

| Improve this Doc View Source

LogProbability

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.

Declaration

[JsonPropertyName("logprobs")]
public int? LogProbability { get; init; }

Property Value

Type	Description
int?

| Improve this Doc View Source

MaxTokens

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

Declaration

[JsonPropertyName("max_tokens")]
public int? MaxTokens { get; set; }

Property Value

Type	Description
int?

Remarks

Could be set to -1 if there a single prompt to return as many tokens as possible given the prompt and the models maximal context size.

| Improve this Doc View Source

Model

The name of the model to use.

Declaration

[JsonPropertyName("model")]
public string Model { get; init; }

Property Value

Type	Description
string

| Improve this Doc View Source

NucleusSamplingFactor

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% probability mass are considered. We generally recommend using this or temperature but not both. Minimum of 0 and maximum of 1 allowed.

Declaration

[JsonPropertyName("top_p")]
public float? NucleusSamplingFactor { get; init; }

Property Value

Type	Description
float?

| Improve this Doc View Source

PresencePenalty

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

Declaration

[JsonPropertyName("presence_penalty")]
public float? PresencePenalty { get; init; }

Property Value

Type	Description
float?

| Improve this Doc View Source

Prompt

An optional prompt to complete from, encoded as a string, a list of strings, or a list of token lists. Defaults to <|endoftext|>. The prompt to complete from. If you would like to provide multiple prompts, use the POST variant of this method. Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. Maximum allowed size of string list is 2048.

Declaration

[JsonPropertyName("prompt")]
public IList<string> Prompt { get; init; }

Property Value

Type	Description
IList<string>

| Improve this Doc View Source

SnippetCount

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

Declaration

[JsonPropertyName("n")]
public int? SnippetCount { get; init; }

Property Value

Type	Description
int?

| Improve this Doc View Source

Stop

A sequence which indicates the end of the current document.

Declaration

[JsonPropertyName("stop")]
public IList<string> Stop { get; set; }

Property Value

Type	Description
IList<string>

| Improve this Doc View Source

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.

Declaration

[JsonPropertyName("temperature")]
public float? Temperature { get; init; }

Property Value

Type	Description
float?

| Improve this Doc View Source

User

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

Declaration

[JsonPropertyName("user")]
public string User { get; init; }

Property Value

Type	Description
string

Implements

System.IEquatable<T>