@ai16z/eliza v0.1.6-alpha.4 / trimTokens
Function: trimTokens()
trimTokens(
context
,maxTokens
,model
):string
Truncate the context to the maximum length allowed by the model.
Parameters
• context: string
The text to truncate
• maxTokens: number
Maximum number of tokens to keep
• model: TiktokenModel
The tokenizer model to use
Returns
string
The truncated text