node-llama-cpp

Appearance

Type Alias: LLamaChatCompletePromptOptions ​

ts
type LLamaChatCompletePromptOptions = {
  maxTokens?: LLamaChatPromptOptions["maxTokens"];
  stopOnAbortSignal?: LLamaChatPromptOptions["stopOnAbortSignal"];
  onTextChunk?: LLamaChatPromptOptions["onTextChunk"];
  onToken?: LLamaChatPromptOptions["onToken"];
  signal?: LLamaChatPromptOptions["signal"];
  temperature?: LLamaChatPromptOptions["temperature"];
  minP?: LLamaChatPromptOptions["minP"];
  topK?: LLamaChatPromptOptions["topK"];
  topP?: LLamaChatPromptOptions["topP"];
  seed?: LLamaChatPromptOptions["seed"];
  trimWhitespaceSuffix?: LLamaChatPromptOptions["trimWhitespaceSuffix"];
  evaluationPriority?: LLamaChatPromptOptions["evaluationPriority"];
  repeatPenalty?: LLamaChatPromptOptions["repeatPenalty"];
  tokenBias?: LLamaChatPromptOptions["tokenBias"];
  customStopTriggers?: LLamaChatPromptOptions["customStopTriggers"];
  grammar?: LlamaGrammar;
  functions?: ChatSessionModelFunctions;
  documentFunctionParams?: boolean;
};

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:227

Properties ​

maxTokens? ​

ts
optional maxTokens: LLamaChatPromptOptions["maxTokens"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:233

Generate a completion for the given user prompt up to the given number of tokens.

Defaults to 256 or half the context size, whichever is smaller.

stopOnAbortSignal? ​

ts
optional stopOnAbortSignal: LLamaChatPromptOptions["stopOnAbortSignal"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:241

When a completion already started being generated and then the given signal is aborted, the generation will stop and the completion will be returned as-is instead of throwing an error.

Defaults to false.

onTextChunk? ​

ts
optional onTextChunk: LLamaChatPromptOptions["onTextChunk"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:248

Called as the model generates a completion with the generated text chunk.

Useful for streaming the generated completion as it's being generated.

onToken? ​

ts
optional onToken: LLamaChatPromptOptions["onToken"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:255

Called as the model generates a completion with the generated tokens.

Preferably, you'd want to use onTextChunk instead of this.

signal? ​

ts
optional signal: LLamaChatPromptOptions["signal"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:257

temperature? ​

ts
optional temperature: LLamaChatPromptOptions["temperature"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:258

minP? ​

ts
optional minP: LLamaChatPromptOptions["minP"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:259

topK? ​

ts
optional topK: LLamaChatPromptOptions["topK"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:260

topP? ​

ts
optional topP: LLamaChatPromptOptions["topP"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:261

seed? ​

ts
optional seed: LLamaChatPromptOptions["seed"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:262

trimWhitespaceSuffix? ​

ts
optional trimWhitespaceSuffix: LLamaChatPromptOptions["trimWhitespaceSuffix"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:263

evaluationPriority? ​

ts
optional evaluationPriority: LLamaChatPromptOptions["evaluationPriority"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:264

repeatPenalty? ​

ts
optional repeatPenalty: LLamaChatPromptOptions["repeatPenalty"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:265

tokenBias? ​

ts
optional tokenBias: LLamaChatPromptOptions["tokenBias"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:266

customStopTriggers? ​

ts
optional customStopTriggers: LLamaChatPromptOptions["customStopTriggers"];

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:267

grammar? ​

ts
optional grammar: LlamaGrammar;

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:269

functions? ​

ts
optional functions: ChatSessionModelFunctions;

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:278

Functions are not used by the model here, but are used for keeping the instructions given to the model about the functions in the current context state, to avoid context shifts.

It's best to provide the same functions that were used for the previous prompt here.

documentFunctionParams? ​

ts
optional documentFunctionParams: boolean;

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:287

Functions are not used by the model here, but are used for keeping the instructions given to the model about the functions in the current context state, to avoid context shifts.

It's best to provide the same value that was used for the previous prompt here.