Skip to main content

Interface: OpenAICompatibleCompletionModelSettings

Hierarchy​

Properties​

api​

• api: OpenAICompatibleApiConfiguration

Overrides​

AbstractOpenAICompletionModelSettings.api

Defined in​

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleCompletionModel.ts:23

bestOf​

• Optional bestOf: number

Inherited from​

AbstractOpenAICompletionModelSettings.bestOf

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:32

echo​

• Optional echo: boolean

Inherited from​

AbstractOpenAICompletionModelSettings.echo

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:29

frequencyPenalty​

• Optional frequencyPenalty: number

Inherited from​

AbstractOpenAICompletionModelSettings.frequencyPenalty

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:31

isUserIdForwardingEnabled​

• Optional isUserIdForwardingEnabled: boolean

Inherited from​

AbstractOpenAICompletionModelSettings.isUserIdForwardingEnabled

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:36

logitBias​

• Optional logitBias: Record<number, number>

Inherited from​

AbstractOpenAICompletionModelSettings.logitBias

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:33

logprobs​

• Optional logprobs: number

Inherited from​

AbstractOpenAICompletionModelSettings.logprobs

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:28

maxGenerationTokens​

• Optional maxGenerationTokens: number

Specifies the maximum number of tokens (words, punctuation, parts of words) that the model can generate in a single response. It helps to control the length of the output.

Does nothing if the model does not support this setting.

Example: maxGenerationTokens: 1000

Inherited from​

AbstractOpenAICompletionModelSettings.maxGenerationTokens

Defined in​

packages/modelfusion/src/model-function/generate-text/TextGenerationModel.ts:28

model​

• model: string

Inherited from​

AbstractOpenAICompletionModelSettings.model

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:23

numberOfGenerations​

• Optional numberOfGenerations: number

Number of texts to generate.

Specifies the number of responses or completions the model should generate for a given prompt. This is useful when you need multiple different outputs or ideas for a single prompt. The model will generate 'n' distinct responses, each based on the same initial prompt. In a streaming model this will result in both responses streamed back in real time.

Does nothing if the model does not support this setting.

Example: numberOfGenerations: 3 // The model will produce 3 different responses.

Inherited from​

AbstractOpenAICompletionModelSettings.numberOfGenerations

Defined in​

packages/modelfusion/src/model-function/generate-text/TextGenerationModel.ts:55

observers​

• Optional observers: FunctionObserver[]

Observers that are called when the model is used in run functions.

Inherited from​

AbstractOpenAICompletionModelSettings.observers

Defined in​

packages/modelfusion/src/model-function/Model.ts:8

presencePenalty​

• Optional presencePenalty: number

Inherited from​

AbstractOpenAICompletionModelSettings.presencePenalty

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:30

provider​

• Optional provider: `openaicompatible-${string}` | "openaicompatible"

Defined in​

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleCompletionModel.ts:24

seed​

• Optional seed: null | number

Inherited from​

AbstractOpenAICompletionModelSettings.seed

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:34

stopSequences​

• Optional stopSequences: string[]

Stop sequences to use. Stop sequences are an array of strings or a single string that the model will recognize as end-of-text indicators. The model stops generating more content when it encounters any of these strings. This is particularly useful in scripted or formatted text generation, where a specific end point is required. Stop sequences not included in the generated text.

Does nothing if the model does not support this setting.

Example: stopSequences: ['\n', 'END']

Inherited from​

AbstractOpenAICompletionModelSettings.stopSequences

Defined in​

packages/modelfusion/src/model-function/generate-text/TextGenerationModel.ts:41

suffix​

• Optional suffix: string

Inherited from​

AbstractOpenAICompletionModelSettings.suffix

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:25

temperature​

• Optional temperature: number

Inherited from​

AbstractOpenAICompletionModelSettings.temperature

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:26

topP​

• Optional topP: number

Inherited from​

AbstractOpenAICompletionModelSettings.topP

Defined in​

packages/modelfusion/src/model-provider/openai/AbstractOpenAICompletionModel.ts:27

trimWhitespace​

• Optional trimWhitespace: boolean

When true, the leading and trailing white space and line terminator characters are removed from the generated text.

Default: true.

Inherited from​

AbstractOpenAICompletionModelSettings.trimWhitespace

Defined in​

packages/modelfusion/src/model-function/generate-text/TextGenerationModel.ts:63