Type Alias: LLamaChatCompletePromptOptions
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;
completeAsModel?: | "auto"
| boolean
| {
enabled?: "auto" | boolean;
appendedMessages?: ChatHistoryItem[];
};
};
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:247
Properties
maxTokens?
optional maxTokens: LLamaChatPromptOptions["maxTokens"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:253
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?
optional stopOnAbortSignal: LLamaChatPromptOptions["stopOnAbortSignal"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:261
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?
optional onTextChunk: LLamaChatPromptOptions["onTextChunk"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:268
Called as the model generates a completion with the generated text chunk.
Useful for streaming the generated completion as it's being generated.
onToken?
optional onToken: LLamaChatPromptOptions["onToken"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:275
Called as the model generates a completion with the generated tokens.
Preferably, you'd want to use onTextChunk
instead of this.
signal?
optional signal: LLamaChatPromptOptions["signal"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:277
temperature?
optional temperature: LLamaChatPromptOptions["temperature"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:278
minP?
optional minP: LLamaChatPromptOptions["minP"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:279
topK?
optional topK: LLamaChatPromptOptions["topK"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:280
topP?
optional topP: LLamaChatPromptOptions["topP"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:281
seed?
optional seed: LLamaChatPromptOptions["seed"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:282
trimWhitespaceSuffix?
optional trimWhitespaceSuffix: LLamaChatPromptOptions["trimWhitespaceSuffix"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:283
evaluationPriority?
optional evaluationPriority: LLamaChatPromptOptions["evaluationPriority"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:284
repeatPenalty?
optional repeatPenalty: LLamaChatPromptOptions["repeatPenalty"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:285
tokenBias?
optional tokenBias: LLamaChatPromptOptions["tokenBias"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:286
customStopTriggers?
optional customStopTriggers: LLamaChatPromptOptions["customStopTriggers"];
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:287
grammar?
optional grammar: LlamaGrammar;
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:289
functions?
optional functions: ChatSessionModelFunctions;
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:298
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?
optional documentFunctionParams: boolean;
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:307
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.
completeAsModel?
optional completeAsModel:
| "auto"
| boolean
| {
enabled?: "auto" | boolean;
appendedMessages?: ChatHistoryItem[];
};
Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:319
Whether to complete the prompt as a model response.
"auto"
: Automatically determine whether to complete as a model response based on the model used. This is a good option to workaround some models that don't support used prompt completions.true
: Always complete as a model responsefalse
: Never complete as a model response
Defaults to "auto"
.
Type declaration
"auto"
boolean
{
enabled?: "auto" | boolean;
appendedMessages?: ChatHistoryItem[];
}
enabled?
optional enabled: "auto" | boolean;
Whether to complete the prompt as a model response.
"auto"
: Automatically determine whether to complete as a model response based on the model used. This is a good option to workaround some models that don't support used prompt completions.true
: Always complete as a model responsefalse
: Never complete as a model response
Defaults to "auto"
.
appendedMessages?
optional appendedMessages: ChatHistoryItem[];
The messages to append to the chat history to generate a completion as a model response.
If the last message is a model message, the prompt will be pushed to it for the completion, otherwise a new model message will be added with the prompt.
It must contain a user message or a system message before the model message.
Default to:
[
{
type: "system",
text: "For your next response predict what the user may send next. No yapping, no whitespace. Match the user's language and tone."
},
{type: "user", text: ""},
{type: "model", response: [""]}
]