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/providers/huggingface/dist/index.d.ts:114

Properties​

contextWindow​

contextWindow: number

Defined in​

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

hf​

hf: HfInference

Defined in​

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

maxTokens?​

optional maxTokens: number

Defined in​

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

model​

model: string

Defined in​

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

temperature​

temperature: number

Defined in​

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

topP​

topP: number

Defined in​

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

Accessors​

metadata​

Get Signature​

get metadata(): LLMMetadata

Returns​

LLMMetadata

Overrides​

BaseLLM.metadata

Defined in​

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

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/providers/huggingface/dist/index.d.ts:116

chat(params)​

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

Parameters​

• params: LLMChatParamsNonStreaming<object, object>

Returns​

Promise<ChatResponse<object>>

Overrides​

BaseLLM.chat

Defined in​

packages/providers/huggingface/dist/index.d.ts:117

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:163

complete(params)​

complete(params): Promise<CompletionResponse>

Parameters​

• params: LLMCompletionParamsNonStreaming

Returns​

Promise<CompletionResponse>

Inherited from​

BaseLLM.complete

Defined in​

packages/core/llms/dist/index.d.ts:164

nonStreamChat()​

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

Parameters​

• params: LLMChatParamsNonStreaming<object, object>

Returns​

Promise<ChatResponse<object>>

Defined in​

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

streamChat()​

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

Parameters​

• params: LLMChatParamsStreaming<object, object>

Returns​

AsyncIterable<ChatResponseChunk, any, any>

Defined in​

packages/providers/huggingface/dist/index.d.ts:120