Class: OpenAI
Hierarchy
-
BaseLLM<OpenAIAdditionalChatOptions>↳
OpenAI↳↳
FireworksLLM↳↳
Groq↳↳
TogetherLLM
Constructors
constructor
• new OpenAI(init?): OpenAI
Parameters
| Name | Type |
|---|---|
init? | Partial<OpenAI> & { azure?: AzureOpenAIConfig } |
Returns
Overrides
BaseLLM<OpenAIAdditionalChatOptions>.constructor
Defined in
packages/core/src/llm/open_ai.ts:172
Properties
additionalChatOptions
• Optional additionalChatOptions: OpenAIAdditionalChatOptions
Defined in
packages/core/src/llm/open_ai.ts:160
additionalSessionOptions
• Optional additionalSessionOptions: Omit<Partial<ClientOptions>, "apiKey" | "timeout" | "maxRetries">
Defined in
packages/core/src/llm/open_ai.ts:167
apiKey
• Optional apiKey: string = undefined
Defined in
packages/core/src/llm/open_ai.ts:163
maxRetries
• maxRetries: number
Defined in
packages/core/src/llm/open_ai.ts:164
maxTokens
• Optional maxTokens: number
Defined in
packages/core/src/llm/open_ai.ts:159
model
• model: string
Defined in
packages/core/src/llm/open_ai.ts:156
session
• session: OpenAISession
Defined in
packages/core/src/llm/open_ai.ts:166
temperature
• temperature: number
Defined in
packages/core/src/llm/open_ai.ts:157
timeout
• Optional timeout: number
Defined in
packages/core/src/llm/open_ai.ts:165
topP
• topP: number
Defined in
packages/core/src/llm/open_ai.ts:158
Accessors
metadata
• get metadata(): LLMMetadata & OpenAIAdditionalMetadata
Returns
LLMMetadata & OpenAIAdditionalMetadata
Overrides
BaseLLM.metadata
Defined in
packages/core/src/llm/open_ai.ts:225
Methods
chat
▸ chat(params): Promise<AsyncIterable<ChatResponseChunk>>
Parameters
| Name | Type |
|---|---|
params | LLMChatParamsStreaming<OpenAIAdditionalChatOptions> |
Returns
Promise<AsyncIterable<ChatResponseChunk>>
Overrides
BaseLLM.chat
Defined in
packages/core/src/llm/open_ai.ts:277
▸ chat(params): Promise<ChatResponse>
Parameters
| Name | Type |
|---|---|
params | LLMChatParamsNonStreaming<OpenAIAdditionalChatOptions> |
Returns
Promise<ChatResponse>
Overrides
BaseLLM.chat
Defined in
packages/core/src/llm/open_ai.ts:280
complete
▸ complete(params): Promise<AsyncIterable<CompletionResponse>>
Parameters
| Name | Type |
|---|---|
params | LLMCompletionParamsStreaming |
Returns
Promise<AsyncIterable<CompletionResponse>>
Inherited from
BaseLLM.complete
Defined in
packages/core/src/llm/base.ts:23
▸ complete(params): Promise<CompletionResponse>
Parameters
| Name | Type |
|---|---|
params | LLMCompletionParamsNonStreaming |
Returns
Promise<CompletionResponse>
Inherited from
BaseLLM.complete
Defined in
packages/core/src/llm/base.ts:26
mapMessageType
▸ mapMessageType(messageType): "function" | "user" | "assistant" | "system" | "tool"
Parameters
| Name | Type |
|---|---|
messageType | MessageType |
Returns
"function" | "user" | "assistant" | "system" | "tool"
Defined in
packages/core/src/llm/open_ai.ts:241
streamChat
▸ streamChat(baseRequestParams): AsyncIterable<ChatResponseChunk>
Parameters
| Name | Type |
|---|---|
baseRequestParams | ChatCompletionCreateParams |
Returns
AsyncIterable<ChatResponseChunk>
Defined in
packages/core/src/llm/open_ai.ts:330
toOpenAIMessage
▸ toOpenAIMessage(messages): { content: MessageContent = message.content; role: "function" | "user" | "assistant" | "system" | "tool" }[]
Parameters
| Name | Type |
|---|---|
messages | ChatMessage[] |
Returns
{ content: MessageContent = message.content; role: "function" | "user" | "assistant" | "system" | "tool" }[]
Defined in
packages/core/src/llm/open_ai.ts:260
toTool
▸ toTool(tool): ChatCompletionTool
Parameters
| Name | Type |
|---|---|
tool | BaseTool |
Returns
ChatCompletionTool