Class: OpenAI
OpenAI LLM implementation
Implements
Constructors
constructor
• new OpenAI(init?)
Parameters
| Name | Type |
|---|---|
init? | Partial<OpenAI> & { azure?: AzureOpenAIConfig } |
Defined in
packages/core/src/llm/LLM.ts:152
Properties
additionalChatOptions
• Optional additionalChatOptions: Omit<Partial<ChatCompletionCreateParams>, "model" | "temperature" | "max_tokens" | "messages" | "top_p" | "streaming">
Defined in
packages/core/src/llm/LLM.ts:135
additionalSessionOptions
• Optional additionalSessionOptions: Omit<Partial<ClientOptions>, "apiKey" | "timeout" | "maxRetries">
Defined in
packages/core/src/llm/LLM.ts:145
apiKey
• Optional apiKey: string = undefined
Defined in
packages/core/src/llm/LLM.ts:141
callbackManager
• Optional callbackManager: CallbackManager
Defined in
packages/core/src/llm/LLM.ts:150
hasStreaming
• hasStreaming: boolean = true
Implementation of
Defined in
packages/core/src/llm/LLM.ts:128
maxRetries
• maxRetries: number
Defined in
packages/core/src/llm/LLM.ts:142
maxTokens
• Optional maxTokens: number
Defined in
packages/core/src/llm/LLM.ts:134
model
• model: "gpt-3.5-turbo" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-16k" | "gpt-4" | "gpt-4-32k" | "gpt-4-1106-preview" | "gpt-4-vision-preview"
Defined in
packages/core/src/llm/LLM.ts:131
session
• session: OpenAISession
Defined in
packages/core/src/llm/LLM.ts:144
temperature
• temperature: number
Defined in
packages/core/src/llm/LLM.ts:132
timeout
• Optional timeout: number
Defined in
packages/core/src/llm/LLM.ts:143
topP
• topP: number
Defined in
packages/core/src/llm/LLM.ts:133
Accessors
metadata
• get metadata(): Object
Returns
Object
| Name | Type |
|---|---|
contextWindow | number |
maxTokens | undefined | number |
model | "gpt-3.5-turbo" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-16k" | "gpt-4" | "gpt-4-32k" | "gpt-4-1106-preview" | "gpt-4-vision-preview" |
temperature | number |
tokenizer | CL100K_BASE |
topP | number |
Implementation of
Defined in
packages/core/src/llm/LLM.ts:206
Methods
chat
▸ chat<T, R>(messages, parentEvent?, streaming?): Promise<R>
Get a chat response from the LLM
Type parameters
| Name | Type |
|---|---|
T | extends undefined | boolean = undefined |
R | T extends true ? AsyncGenerator<string, void, unknown> : ChatResponse |
Parameters
| Name | Type | Description |
|---|---|---|
messages | ChatMessage[] | The return type of chat() and complete() are set by the "streaming" parameter being set to True. |
parentEvent? | Event | - |
streaming? | T | - |
Returns
Promise<R>
Implementation of
Defined in
packages/core/src/llm/LLM.ts:249
complete
▸ complete<T, R>(prompt, parentEvent?, streaming?): Promise<R>
Get a prompt completion from the LLM
Type parameters
| Name | Type |
|---|---|
T | extends undefined | boolean = undefined |
R | T extends true ? AsyncGenerator<string, void, unknown> : ChatResponse |
Parameters
| Name | Type | Description |
|---|---|---|
prompt | string | the prompt to complete |
parentEvent? | Event | - |
streaming? | T | - |
Returns
Promise<R>
Implementation of
Defined in
packages/core/src/llm/LLM.ts:286
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:232
streamChat
▸ Protected streamChat(messages, parentEvent?): AsyncGenerator<string, void, unknown>
Parameters
| Name | Type |
|---|---|
messages | ChatMessage[] |
parentEvent? | Event |
Returns
AsyncGenerator<string, void, unknown>
Defined in
packages/core/src/llm/LLM.ts:300
streamComplete
▸ Protected streamComplete(query, parentEvent?): AsyncGenerator<string, void, unknown>
Parameters
| Name | Type |
|---|---|
query | string |
parentEvent? | Event |
Returns
AsyncGenerator<string, void, unknown>
Defined in
packages/core/src/llm/LLM.ts:362
tokens
▸ tokens(messages): number
Calculates the number of tokens needed for the given chat messages
Parameters
| Name | Type |
|---|---|
messages | ChatMessage[] |
Returns
number