A platform for community discussion. Free, open, simple.
# frozen_string_literal: true
module DiscourseAi
module Completions
class TokenUsageTracker
def initialize(base_total: nil, base_request: nil, base_response: nil, base_preparation: 0)
@mutex = Mutex.new
@preparation_tokens = base_preparation.to_i
if base_request.nil? && base_response.nil?
total = base_total.to_i
initial_request = total / 2
@request = initial_request
@response = total - initial_request
else
if !base_total.nil?
raise ArgumentError, "base_total cannot be combined with base_request/base_response"
end
if base_request.nil? || base_response.nil?
raise ArgumentError, "base_request and base_response must both be provided"
end
@request = base_request.to_i
@response = base_response.to_i
end
end
def add_from_audit_log(log, preparation: false)
# request_tokens = non-cached input (already excludes cached)
# cache_write_tokens = newly cached (full cost)
# cache_read_tokens = served from cache (1/10 cost)
request =
log.request_tokens.to_i + log.cache_write_tokens.to_i +
(log.cache_read_tokens.to_i * 0.1).to_i
response = log.response_tokens.to_i
request = estimate_tokens(raw_payload(log, :raw_request_payload)) if request <= 0
response = estimate_tokens(raw_payload(log, :raw_response_payload)) if response <= 0
add_effective(request: request, response: response, preparation: preparation)
end
def raw_payload(log, name)
log.public_send(name) if log.respond_to?(name)
end
def estimate_tokens(payload)
return 0 if payload.blank?
(payload.to_s.bytesize / 3.0).ceil
end
def add_effective(request:, response:, preparation: false)
@mutex.synchronize do
@request += request.to_i
@response += response.to_i
@preparation_tokens += request.to_i + response.to_i if preparation
end
end
def request
@mutex.synchronize { @request }
end
def response
@mutex.synchronize { @response }
end
def preparation_tokens
@mutex.synchronize { @preparation_tokens }
end
def total
@mutex.synchronize { @request + @response }
end
end
end
end