Interface: LLM
Unified language model interface
Implemented by
Properties
hasStreaming
• hasStreaming: boolean
Defined in
packages/core/src/llm/LLM.ts:68
metadata
• metadata: LLMMetadata
Defined in
packages/core/src/llm/LLM.ts:66
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>
Defined in
packages/core/src/llm/LLM.ts:75
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>
Defined in
packages/core/src/llm/LLM.ts:88
tokens
▸ tokens(messages): number
Calculates the number of tokens needed for the given chat messages
Parameters
| Name | Type |
|---|---|
messages | ChatMessage[] |
Returns
number