Class: OpenAI
Hierarchy
-
ToolCallLLM<OpenAIAdditionalChatOptions>↳
OpenAI↳↳
FireworksLLM↳↳
Groq↳↳
TogetherLLM
Constructors
constructor
• new OpenAI(init?): OpenAI
Parameters
| Name | Type |
|---|---|
init? | Partial<OpenAI> & { azure?: AzureOpenAIConfig } |
Returns
Overrides
ToolCallLLM<OpenAIAdditionalChatOptions>.constructor
Defined in
packages/core/src/llm/openai.ts:179
Properties
additionalChatOptions
• Optional additionalChatOptions: OpenAIAdditionalChatOptions
Defined in
packages/core/src/llm/openai.ts:167
additionalSessionOptions
• Optional additionalSessionOptions: Omit<Partial<ClientOptions>, "apiKey" | "timeout" | "maxRetries">
Defined in
packages/core/src/llm/openai.ts:174
apiKey
• Optional apiKey: string = undefined
Defined in
packages/core/src/llm/openai.ts:170
maxRetries
• maxRetries: number
Defined in
packages/core/src/llm/openai.ts:171
maxTokens
• Optional maxTokens: number
Defined in
packages/core/src/llm/openai.ts:166
model
• model: string
Defined in
packages/core/src/llm/openai.ts:163
session
• session: OpenAISession
Defined in
packages/core/src/llm/openai.ts:173
temperature
• temperature: number
Defined in
packages/core/src/llm/openai.ts:164
timeout
• Optional timeout: number
Defined in
packages/core/src/llm/openai.ts:172
topP
• topP: number
Defined in
packages/core/src/llm/openai.ts:165
Accessors
metadata
• get metadata(): LLMMetadata
Returns
Overrides
ToolCallLLM.metadata
Defined in
packages/core/src/llm/openai.ts:236
supportToolCall
• get supportToolCall(): boolean
Returns
boolean
Overrides
ToolCallLLM.supportToolCall
Defined in
packages/core/src/llm/openai.ts:232
Methods
chat
▸ chat(params): Promise<AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>>
Parameters
| Name | Type |
|---|---|
params | LLMChatParamsStreaming<OpenAIAdditionalChatOptions, ToolCallLLMMessageOptions> |
Returns
Promise<AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>>
Overrides
ToolCallLLM.chat
Defined in
packages/core/src/llm/openai.ts:313
▸ chat(params): Promise<ChatResponse<ToolCallLLMMessageOptions>>
Parameters
| Name | Type |
|---|---|
params | LLMChatParamsNonStreaming<OpenAIAdditionalChatOptions, ToolCallLLMMessageOptions> |
Returns
Promise<ChatResponse<ToolCallLLMMessageOptions>>
Overrides
ToolCallLLM.chat
Defined in
packages/core/src/llm/openai.ts:319
complete
▸ complete(params): Promise<AsyncIterable<CompletionResponse>>
Parameters
| Name | Type |
|---|---|
params | LLMCompletionParamsStreaming |
Returns
Promise<AsyncIterable<CompletionResponse>>
Inherited from
ToolCallLLM.complete
Defined in
packages/core/src/llm/base.ts:22
▸ complete(params): Promise<CompletionResponse>
Parameters
| Name | Type |
|---|---|
params | LLMCompletionParamsNonStreaming |
Returns
Promise<CompletionResponse>
Inherited from
ToolCallLLM.complete
Defined in
packages/core/src/llm/base.ts:25
streamChat
▸ streamChat(baseRequestParams): AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>
Parameters
| Name | Type |
|---|---|
baseRequestParams | ChatCompletionCreateParams |
Returns
AsyncIterable<ChatResponseChunk<ToolCallLLMMessageOptions>>
Defined in
packages/core/src/llm/openai.ts:385
toOpenAIMessage
▸ toOpenAIMessage(messages): ChatCompletionMessageParam[]
Parameters
| Name | Type |
|---|---|
messages | ChatMessage<ToolCallLLMMessageOptions>[] |
Returns
ChatCompletionMessageParam[]
Defined in
packages/core/src/llm/openai.ts:264
toOpenAIRole
▸ toOpenAIRole(messageType): ChatCompletionRole
Parameters
| Name | Type |
|---|---|
messageType | MessageType |
Returns
ChatCompletionRole
Defined in
packages/core/src/llm/openai.ts:251
toTool
▸ toTool(tool): ChatCompletionTool
Parameters
| Name | Type |
|---|---|
tool | BaseTool<any> |
Returns
ChatCompletionTool