Class: LlamaChatSession

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:300

See

Using LlamaChatSession tutorial

Constructors

new LlamaChatSession()

new LlamaChatSession(options: LlamaChatSessionOptions): LlamaChatSession

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:315

Parameters

Parameter	Type
options	LlamaChatSessionOptions

Returns

LlamaChatSession

Properties

onDispose

readonly onDispose: EventRelay<void>;

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:313

Accessors

disposed

Get Signature

get disposed(): boolean

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:372

Returns

boolean

---

chatWrapper

Get Signature

get chatWrapper(): ChatWrapper

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:376

Returns

ChatWrapper

---

sequence

Get Signature

get sequence(): LlamaContextSequence

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:383

Returns

LlamaContextSequence

---

context

Get Signature

get context(): LlamaContext

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:390

Returns

LlamaContext

---

model

Get Signature

get model(): LlamaModel

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:394

Returns

LlamaModel

Methods

dispose()

dispose(__namedParameters: {
  disposeSequence: boolean;
 }): void

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:357

Parameters

Parameter	Type
__namedParameters	{ disposeSequence: boolean; }
__namedParameters.disposeSequence?	boolean

Returns

void

---

prompt()

prompt<Functions>(prompt: string, options: LLamaChatPromptOptions<Functions>): Promise<string>

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:398

Type Parameters

Type Parameter	Default type
Functions extends | undefined | ChatSessionModelFunctions	undefined

Parameters

Parameter	Type
prompt	string
options	LLamaChatPromptOptions<Functions>

Returns

Promise<string>

---

promptWithMeta()

promptWithMeta<Functions>(prompt: string, options?: LLamaChatPromptOptions<Functions>): Promise<
  | {
  response: (
     | string
     | ChatModelFunctionCall)[];
  responseText: string;
  stopReason: "customStopTrigger";
  customStopTrigger: (string | Token)[];
  remainingGenerationAfterStop: undefined | string | Token[];
 }
  | {
  customStopTrigger: undefined;
  response: (
     | string
     | ChatModelFunctionCall)[];
  responseText: string;
  stopReason:   | "abort"
     | "maxTokens"
     | "eogToken"
     | "stopGenerationTrigger"
     | "functionCalls";
  remainingGenerationAfterStop: undefined | string | Token[];
 }>

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:441

Type Parameters

Type Parameter	Default type
Functions extends | undefined | ChatSessionModelFunctions	undefined

Parameters

Parameter	Type	Description
prompt	string
options?	LLamaChatPromptOptions<Functions>

Returns

Promise< | { response: ( | string | ChatModelFunctionCall)[]; responseText: string; stopReason: "customStopTrigger"; customStopTrigger: (string | Token)[]; remainingGenerationAfterStop: undefined | string | Token[]; } | { customStopTrigger: undefined; response: ( | string | ChatModelFunctionCall)[]; responseText: string; stopReason: | "abort" | "maxTokens" | "eogToken" | "stopGenerationTrigger" | "functionCalls"; remainingGenerationAfterStop: undefined | string | Token[]; }>

---

preloadPrompt()

preloadPrompt(prompt: string, options?: LLamaChatPreloadPromptOptions): Promise<void>

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:699

Preload a user prompt into the current context sequence state to make later inference of the model response begin sooner and feel faster.

Note: Preloading a long user prompt can incur context shifts, so consider limiting the length of prompts you preload

Parameters

Parameter	Type	Description
prompt	string	the prompt to preload
options?	LLamaChatPreloadPromptOptions

Returns

Promise<void>

---

completePrompt()

completePrompt(prompt: string, options?: LLamaChatCompletePromptOptions): Promise<string>

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:716

Preload a user prompt into the current context sequence state and generate a completion for it.

Note: Preloading a long user prompt and completing a user prompt with a high number of maxTokens can incur context shifts, so consider limiting the length of prompts you preload.

Also, it's recommended to limit the number of tokens generated to a reasonable amount by configuring maxTokens.

Parameters

Parameter	Type	Description
prompt	string	the prompt to preload
options?	LLamaChatCompletePromptOptions

Returns

Promise<string>

---

createPromptCompletionEngine()

createPromptCompletionEngine(options?: LLamaChatPromptCompletionEngineOptions): LlamaChatSessionPromptCompletionEngine

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:729

Create a smart completion engine that caches the prompt completions and reuses them when the user prompt matches the beginning of the cached prompt or completion.

All completions are made and cache is used only for the current chat session state. You can create a single completion engine for an entire chat session.

Parameters

Parameter	Type
options?	LLamaChatPromptCompletionEngineOptions

Returns

LlamaChatSessionPromptCompletionEngine

---

completePromptWithMeta()

completePromptWithMeta(prompt: string, options?: LLamaChatCompletePromptOptions): Promise<
  | {
  completion: string;
  stopReason: "customStopTrigger";
  customStopTrigger: (string | Token)[];
  remainingGenerationAfterStop: undefined | string | Token[];
 }
  | {
  customStopTrigger: undefined;
  completion: string;
  stopReason: "abort" | "maxTokens" | "eogToken" | "stopGenerationTrigger";
  remainingGenerationAfterStop: undefined | string | Token[];
 }>

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:738

See completePrompt for more information.

Parameters

Parameter	Type	Description
prompt	string
options?	LLamaChatCompletePromptOptions

Returns

Promise< | { completion: string; stopReason: "customStopTrigger"; customStopTrigger: (string | Token)[]; remainingGenerationAfterStop: undefined | string | Token[]; } | { customStopTrigger: undefined; completion: string; stopReason: "abort" | "maxTokens" | "eogToken" | "stopGenerationTrigger"; remainingGenerationAfterStop: undefined | string | Token[]; }>

---

getChatHistory()

getChatHistory(): ChatHistoryItem[]

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:838

Returns

ChatHistoryItem[]

---

getLastEvaluationContextWindow()

getLastEvaluationContextWindow(): null | ChatHistoryItem[]

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:842

Returns

null | ChatHistoryItem[]

---

setChatHistory()

setChatHistory(chatHistory: ChatHistoryItem[]): void

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:849

Parameters

Parameter	Type
chatHistory	ChatHistoryItem[]

Returns

void

---

resetChatHistory()

resetChatHistory(): void

Defined in: evaluator/LlamaChatSession/LlamaChatSession.ts:856

Clear the chat history and reset it to the initial state.

Returns

void