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: HFConfig

Returns​

HuggingFaceInferenceAPI

Overrides​

BaseLLM . constructor

Source​

packages/llamaindex/src/llm/huggingface.ts:88

Properties​

contextWindow​

contextWindow: number

Source​

packages/llamaindex/src/llm/huggingface.ts:85

hf​

hf: HfInference

Source​

packages/llamaindex/src/llm/huggingface.ts:86

maxTokens?​

optional maxTokens: number

Source​

packages/llamaindex/src/llm/huggingface.ts:84

model​

model: string

Source​

packages/llamaindex/src/llm/huggingface.ts:81

temperature​

temperature: number

Source​

packages/llamaindex/src/llm/huggingface.ts:82

topP​

topP: number

Source​

packages/llamaindex/src/llm/huggingface.ts:83

Accessors​

metadata​

get metadata(): LLMMetadata

Returns​

LLMMetadata

Source​

packages/llamaindex/src/llm/huggingface.ts:109

Methods​

chat()​

chat(params)​

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

Get a chat response from the LLM

Parameters​

• params: LLMChatParamsStreaming<object, object>

Returns​

Promise<AsyncIterable <ChatResponseChunk>>

Overrides​

BaseLLM . chat

Source​

packages/llamaindex/src/llm/huggingface.ts:120

chat(params)​

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

Parameters​

• params: LLMChatParamsNonStreaming<object, object>

Returns​

Promise <ChatResponse<object>>

Overrides​

BaseLLM . chat

Source​

packages/llamaindex/src/llm/huggingface.ts:123

complete()​

complete(params)​

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

Get a prompt completion from the LLM

Parameters​

• params: LLMCompletionParamsStreaming

Returns​

Promise<AsyncIterable <CompletionResponse>>

Inherited from​

BaseLLM . complete

Source​

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

complete(params)​

complete(params): Promise <CompletionResponse>

Parameters​

• params: LLMCompletionParamsNonStreaming

Returns​

Promise <CompletionResponse>

Inherited from​

BaseLLM . complete

Source​

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

messagesToPrompt()​

private messagesToPrompt(messages): string

Parameters​

• messages: ChatMessage <ToolCallLLMMessageOptions>[]

Returns​

string

Source​

packages/llamaindex/src/llm/huggingface.ts:132

nonStreamChat()​

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

Parameters​

• params: LLMChatParamsNonStreaming<object, object>

Returns​

Promise <ChatResponse<object>>

Source​

packages/llamaindex/src/llm/huggingface.ts:152

streamChat()​

protected streamChat(params): AsyncIterable <ChatResponseChunk>

Parameters​

• params: LLMChatParamsStreaming<object, object>

Returns​

AsyncIterable <ChatResponseChunk>

Source​

packages/llamaindex/src/llm/huggingface.ts:169