Skip to main content

Class: HuggingFaceInferenceAPI

Wrapper on the Hugging Face's Inference API. API Docs: https://huggingface.co/docs/huggingface.js/inference/README List of tasks with models: huggingface.co/api/tasks

Note that Conversational API is not yet supported by the Inference API. They recommend using the text generation API instead. See: https://github.com/huggingface/huggingface.js/issues/586#issuecomment-2024059308

Extends

Constructors

new HuggingFaceInferenceAPI()

new HuggingFaceInferenceAPI(init): HuggingFaceInferenceAPI

Parameters

init: any

Returns

HuggingFaceInferenceAPI

Overrides

BaseLLM.constructor

Defined in

packages/embedding/huggingface/dist/index.d.ts:113

Properties

contextWindow

contextWindow: number

Defined in

packages/embedding/huggingface/dist/index.d.ts:111


hf

hf: HfInference

Defined in

packages/embedding/huggingface/dist/index.d.ts:112


maxTokens?

optional maxTokens: number

Defined in

packages/embedding/huggingface/dist/index.d.ts:110


model

model: string

Defined in

packages/embedding/huggingface/dist/index.d.ts:107


temperature

temperature: number

Defined in

packages/embedding/huggingface/dist/index.d.ts:108


topP

topP: number

Defined in

packages/embedding/huggingface/dist/index.d.ts:109

Accessors

metadata

get metadata(): LLMMetadata

Returns

LLMMetadata

Overrides

BaseLLM.metadata

Defined in

packages/embedding/huggingface/dist/index.d.ts:114

Methods

chat()

chat(params)

chat(params): Promise<AsyncIterable<ChatResponseChunk, any, any>>

Get a chat response from the LLM

Parameters

params: LLMChatParamsStreaming<object, object>

Returns

Promise<AsyncIterable<ChatResponseChunk, any, any>>

Overrides

BaseLLM.chat

Defined in

packages/embedding/huggingface/dist/index.d.ts:115

chat(params)

chat(params): Promise<ChatResponse<object>>

Get a chat response from the LLM

Parameters

params: LLMChatParamsNonStreaming<object, object>

Returns

Promise<ChatResponse<object>>

Overrides

BaseLLM.chat

Defined in

packages/embedding/huggingface/dist/index.d.ts:116


complete()

complete(params)

complete(params): Promise<AsyncIterable<CompletionResponse, any, any>>

Get a prompt completion from the LLM

Parameters

params: LLMCompletionParamsStreaming

Returns

Promise<AsyncIterable<CompletionResponse, any, any>>

Inherited from

BaseLLM.complete

Defined in

packages/core/llms/dist/index.d.ts:168

complete(params)

complete(params): Promise<CompletionResponse>

Get a prompt completion from the LLM

Parameters

params: LLMCompletionParamsNonStreaming

Returns

Promise<CompletionResponse>

Inherited from

BaseLLM.complete

Defined in

packages/core/llms/dist/index.d.ts:169


nonStreamChat()

protected nonStreamChat(params): Promise<ChatResponse<object>>

Parameters

params: LLMChatParamsNonStreaming<object, object>

Returns

Promise<ChatResponse<object>>

Defined in

packages/embedding/huggingface/dist/index.d.ts:118


streamChat()

protected streamChat(params): AsyncIterable<ChatResponseChunk, any, any>

Parameters

params: LLMChatParamsStreaming<object, object>

Returns

AsyncIterable<ChatResponseChunk, any, any>

Defined in

packages/embedding/huggingface/dist/index.d.ts:119