Skip to main content

Class: HuggingFaceLLM

Unified language model interface

Extends​

Constructors​

new HuggingFaceLLM()​

new HuggingFaceLLM(init?): HuggingFaceLLM

Parameters​

• init?: HFLLMConfig

Returns​

HuggingFaceLLM

Overrides​

BaseLLM.constructor

Defined in​

packages/llamaindex/src/llm/huggingface.ts:208

Properties​

contextWindow​

contextWindow: number

Defined in​

packages/llamaindex/src/llm/huggingface.ts:203

maxTokens?​

optional maxTokens: number

Defined in​

packages/llamaindex/src/llm/huggingface.ts:202

modelName​

modelName: string

Defined in​

packages/llamaindex/src/llm/huggingface.ts:198

temperature​

temperature: number

Defined in​

packages/llamaindex/src/llm/huggingface.ts:200

tokenizerName​

tokenizerName: string

Defined in​

packages/llamaindex/src/llm/huggingface.ts:199

topP​

topP: number

Defined in​

packages/llamaindex/src/llm/huggingface.ts:201

Accessors​

metadata​

get metadata(): LLMMetadata

Returns​

LLMMetadata

Overrides​

BaseLLM.metadata

Defined in​

packages/llamaindex/src/llm/huggingface.ts:218

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/llamaindex/src/llm/huggingface.ts:261

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/llamaindex/src/llm/huggingface.ts:264

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

getModel()​

getModel(): Promise<PreTrainedModel>

Returns​

Promise<PreTrainedModel>

Defined in​

packages/llamaindex/src/llm/huggingface.ts:245

getTokenizer()​

getTokenizer(): Promise<PreTrainedTokenizer>

Returns​

Promise<PreTrainedTokenizer>

Defined in​

packages/llamaindex/src/llm/huggingface.ts:229

nonStreamChat()​

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

Parameters​

• params: LLMChatParamsNonStreaming<object, object>

Returns​

Promise<ChatResponse<object>>

Defined in​

packages/llamaindex/src/llm/huggingface.ts:273

streamChat()​

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

Parameters​

• params: LLMChatParamsStreaming<object, object>

Returns​

AsyncIterable<ChatResponseChunk, any, any>

Defined in​

packages/llamaindex/src/llm/huggingface.ts:305