Class: LlamaCompletion

Defined in: evaluator/LlamaCompletion.ts:181

See

Text Completion tutorial

Constructors

Constructor

new LlamaCompletion(__namedParameters: LlamaCompletionOptions): LlamaCompletion;

Defined in: evaluator/LlamaCompletion.ts:187

Parameters

Parameter	Type
__namedParameters	LlamaCompletionOptions

Returns

LlamaCompletion

Properties

onDispose

readonly onDispose: EventRelay<void>;

Defined in: evaluator/LlamaCompletion.ts:185

Accessors

disposed

Get Signature

get disposed(): boolean;

Defined in: evaluator/LlamaCompletion.ts:219

Returns

boolean

---

infillSupported

Get Signature

get infillSupported(): boolean;

Defined in: evaluator/LlamaCompletion.ts:223

Returns

boolean

Methods

dispose()

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

Defined in: evaluator/LlamaCompletion.ts:202

Parameters

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

Returns

void

---

generateCompletion()

generateCompletion(input: 
  | string
  | LlamaText
  | Token[], options: LlamaCompletionGenerationOptions): Promise<string>;

Defined in: evaluator/LlamaCompletion.ts:234

Generate a completion for an input.

Parameters

Parameter	Type
input	| string | LlamaText | Token[]
options	LlamaCompletionGenerationOptions

Returns

Promise<string>

---

generateCompletionWithMeta()

generateCompletionWithMeta(input: 
  | string
  | LlamaText
  | Token[], __namedParameters: LlamaCompletionGenerationOptions): Promise<LlamaCompletionResponse>;

Defined in: evaluator/LlamaCompletion.ts:244

Same as generateCompletion, but returns additional metadata about the generation. See generateCompletion for more information.

Parameters

Parameter	Type
input	| string | LlamaText | Token[]
__namedParameters	LlamaCompletionGenerationOptions

Returns

Promise<LlamaCompletionResponse>

---

generateInfillCompletion()

generateInfillCompletion(
   prefixInput: 
  | string
  | LlamaText
  | Token[], 
   suffixInput: 
  | string
  | LlamaText
  | Token[], 
   options: LlamaInfillGenerationOptions): Promise<string>;

Defined in: evaluator/LlamaCompletion.ts:372

Infill (also known as Fill-In-Middle), generates a completion for an input (prefixInput) that should connect to a given continuation (suffixInput). For example, for prefixInput: "123" and suffixInput: "789", the model is expected to generate 456 to make the final text be 123456789.

Parameters

Parameter	Type
prefixInput	| string | LlamaText | Token[]
suffixInput	| string | LlamaText | Token[]
options	LlamaInfillGenerationOptions

Returns

Promise<string>

---

generateInfillCompletionWithMeta()

generateInfillCompletionWithMeta(
   prefixInput: 
  | string
  | LlamaText
  | Token[], 
   suffixInput: 
  | string
  | LlamaText
  | Token[], 
   __namedParameters: LlamaInfillGenerationOptions): Promise<LlamaCompletionResponse>;

Defined in: evaluator/LlamaCompletion.ts:386

Same as generateInfillCompletion, but returns additional metadata about the generation. See generateInfillCompletion for more information.

Parameters

Parameter	Type
prefixInput	| string | LlamaText | Token[]
suffixInput	| string | LlamaText | Token[]
__namedParameters	LlamaInfillGenerationOptions

Returns

Promise<LlamaCompletionResponse>