Class: BaseLLM

Unified language model interface

Hierarchy

• BaseLLM

  ↳ OpenAI

  ↳ LlamaDeuce

  ↳ Anthropic

  ↳ Portkey

  ↳ MistralAI

Implements

• LLM

Constructors

constructor

• new BaseLLM()

Properties

metadata

• Abstract metadata: LLMMetadata

Implementation of

LLM.metadata

Defined in

packages/core/src/llm/LLM.ts:128

Methods

chat

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

Get a chat response from the LLM

Parameters

Name	Type
params	LLMChatParamsStreaming

Returns

Promise<AsyncIterable<ChatResponseChunk>>

Implementation of

LLM.chat

Defined in

packages/core/src/llm/LLM.ts:163

▸ Abstract chat(params): Promise<ChatResponse>

Parameters

Name	Type
params	LLMChatParamsNonStreaming

Returns

Promise<ChatResponse>

Implementation of

LLM.chat

Defined in

packages/core/src/llm/LLM.ts:166

---

chatToComplete

▸ Private chatToComplete(stream): AsyncIterable<CompletionResponse>

Parameters

Name	Type
stream	AsyncIterable<ChatResponseChunk>

Returns

AsyncIterable<CompletionResponse>

Defined in

packages/core/src/llm/LLM.ts:130

---

complete

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

Get a prompt completion from the LLM

Parameters

Name	Type
params	LLMCompletionParamsStreaming

Returns

Promise<AsyncIterable<CompletionResponse>>

Implementation of

LLM.complete

Defined in

packages/core/src/llm/LLM.ts:138

▸ complete(params): Promise<CompletionResponse>

Parameters

Name	Type
params	LLMCompletionParamsNonStreaming

Returns

Promise<CompletionResponse>

Implementation of

LLM.complete

Defined in

packages/core/src/llm/LLM.ts:141

---

tokens

▸ Abstract tokens(messages): number

Calculates the number of tokens needed for the given chat messages

Parameters

Name	Type
messages	ChatMessage[]

Returns

number

Implementation of

LLM.tokens

Defined in

packages/core/src/llm/LLM.ts:168