Class: OpenAI

OpenAI LLM implementation

Hierarchy

• BaseLLM

  ↳ OpenAI

  ↳↳ TogetherLLM

Constructors

constructor

• new OpenAI(init?)

Parameters

Name	Type
init?	Partial<OpenAI> & { azure?: AzureOpenAIConfig }

Overrides

BaseLLM.constructor

Defined in

packages/core/src/llm/LLM.ts:218

Properties

additionalChatOptions

• Optional additionalChatOptions: Omit<Partial<ChatCompletionCreateParams>, "stream" | "max_tokens" | "messages" | "model" | "temperature" | "top_p">

Defined in

packages/core/src/llm/LLM.ts:201

---

additionalSessionOptions

• Optional additionalSessionOptions: Omit<Partial<ClientOptions>, "apiKey" | "timeout" | "maxRetries">

Defined in

packages/core/src/llm/LLM.ts:211

---

apiKey

• Optional apiKey: string = undefined

Defined in

packages/core/src/llm/LLM.ts:207

---

callbackManager

• Optional callbackManager: CallbackManager

Defined in

packages/core/src/llm/LLM.ts:216

---

maxRetries

• maxRetries: number

Defined in

packages/core/src/llm/LLM.ts:208

---

maxTokens

• Optional maxTokens: number

Defined in

packages/core/src/llm/LLM.ts:200

---

model

• model: string

Defined in

packages/core/src/llm/LLM.ts:197

---

session

• session: OpenAISession

Defined in

packages/core/src/llm/LLM.ts:210

---

temperature

• temperature: number

Defined in

packages/core/src/llm/LLM.ts:198

---

timeout

• Optional timeout: number

Defined in

packages/core/src/llm/LLM.ts:209

---

topP

• topP: number

Defined in

packages/core/src/llm/LLM.ts:199

Accessors

metadata

• get metadata(): Object

Returns

Object

Name	Type
contextWindow	number
maxTokens	undefined | number
model	string
temperature	number
tokenizer	CL100K_BASE
topP	number

Overrides

BaseLLM.metadata

Defined in

packages/core/src/llm/LLM.ts:273

Methods

chat

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

Get a chat response from the LLM

Parameters

Name	Type
params	LLMChatParamsStreaming

Returns

Promise<AsyncIterable<ChatResponseChunk>>

Overrides

BaseLLM.chat

Defined in

packages/core/src/llm/LLM.ts:320

▸ chat(params): Promise<ChatResponse>

Parameters

Name	Type
params	LLMChatParamsNonStreaming

Returns

Promise<ChatResponse>

Overrides

BaseLLM.chat

Defined in

packages/core/src/llm/LLM.ts:323

---

complete

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

Get a prompt completion from the LLM

Parameters

Name	Type
params	LLMCompletionParamsStreaming

Returns

Promise<AsyncIterable<CompletionResponse>>

Inherited from

BaseLLM.complete

Defined in

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

▸ complete(params): Promise<CompletionResponse>

Parameters

Name	Type
params	LLMCompletionParamsNonStreaming

Returns

Promise<CompletionResponse>

Inherited from

BaseLLM.complete

Defined in

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

---

mapMessageType

▸ mapMessageType(messageType): "function" | "user" | "assistant" | "system"

Parameters

Name	Type
messageType	MessageType

Returns

"function" | "user" | "assistant" | "system"

Defined in

packages/core/src/llm/LLM.ts:303

---

streamChat

▸ Protected streamChat(«destructured»): AsyncIterable<ChatResponseChunk>

Parameters

Name	Type
«destructured»	LLMChatParamsStreaming

Returns

AsyncIterable<ChatResponseChunk>

Defined in

packages/core/src/llm/LLM.ts:358

---

tokens

▸ tokens(messages): number

Calculates the number of tokens needed for the given chat messages

Parameters

Name	Type
messages	ChatMessage[]

Returns

number

Overrides

BaseLLM.tokens

Defined in

packages/core/src/llm/LLM.ts:288