Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
func CountTokensGlobal ¶
CountTokensGlobal provides a convenient global function for token counting. It uses a singleton TokenCounter instance.
Types ¶
type TokenCounter ¶
type TokenCounter struct {
// contains filtered or unexported fields
}
TokenCounter provides token counting functionality using tiktoken with cl100k_base encoding. This encoding is used for: - GPT-4, GPT-3.5-turbo models - text-embedding-ada-002 - Webhook/BYOW cost calculation (standardized token counting) - Groq models (compatible encoding)
func NewTokenCounter ¶
func NewTokenCounter() (*TokenCounter, error)
NewTokenCounter creates a new token counter using cl100k_base encoding. This is the standard encoding for modern OpenAI models and our webhook pricing. It's also compatible with Groq models for consistent token counting across providers.
func (*TokenCounter) CalculateBYOWCost ¶
func (tc *TokenCounter) CalculateBYOWCost(inputTokens, outputTokens int64) float64
CalculateBYOWCost calculates the cost for Bring Your Own Workflow based on token counts. Pricing: - Input tokens: $0.03 per 1M tokens - Output tokens: $0.12 per 1M tokens
func (*TokenCounter) CountTokens ¶
func (tc *TokenCounter) CountTokens(text string) int
CountTokens counts the number of tokens in the given text using cl100k_base encoding. This is used for: - BYOW (Bring Your Own Workflow) pricing: $0.03 per 1M input tokens, $0.12 per 1M output tokens - Accounting/billing purposes - Pre-request estimation
func (*TokenCounter) CountTokensMultiple ¶
func (tc *TokenCounter) CountTokensMultiple(texts []string) int
CountTokensMultiple counts tokens for multiple text strings and returns the total. Useful for counting tokens across multiple messages in a conversation.
Source Files