mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-02-07 20:18:16 +00:00
d07cf51653
Adds a comprehensive quota management system for LLM models that allows: - Setting per-group (applied per user in the group) token and usage limits with configurable durations - Tracking and enforcing token/usage limits across user groups - Quota reset periods (hourly, daily, weekly, or custom) - Admin UI for managing quotas with real-time updates This system provides granular control over LLM API usage by allowing admins to define limits on both total tokens and number of requests per group. Supports multiple concurrent quotas per model and automatically handles quota resets. Co-authored-by: Keegan George <kgeorge13@gmail.com>
50 lines
1.2 KiB
Ruby
50 lines
1.2 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
class LlmModelSerializer < ApplicationSerializer
|
|
# TODO: we probably should rename the table LlmModel to AiLlm
|
|
# it is consistent with AiPersona and AiTool
|
|
# LLM model is a bit confusing given that large langauge model model is a confusing
|
|
# name
|
|
root "ai_llm"
|
|
attributes :id,
|
|
:display_name,
|
|
:name,
|
|
:provider,
|
|
:max_prompt_tokens,
|
|
:tokenizer,
|
|
:api_key,
|
|
:url,
|
|
:enabled_chat_bot,
|
|
:provider_params,
|
|
:vision_enabled,
|
|
:used_by
|
|
|
|
has_one :user, serializer: BasicUserSerializer, embed: :object
|
|
has_many :llm_quotas, serializer: LlmQuotaSerializer, embed: :objects
|
|
|
|
def used_by
|
|
llm_usage =
|
|
(
|
|
if (scope && scope[:llm_usage])
|
|
scope[:llm_usage]
|
|
else
|
|
DiscourseAi::Configuration::LlmEnumerator.global_usage
|
|
end
|
|
)
|
|
|
|
llm_usage[object.id]
|
|
end
|
|
|
|
def api_key
|
|
object.seeded? ? "********" : object.api_key
|
|
end
|
|
|
|
def url
|
|
object.seeded? ? "********" : object.url
|
|
end
|
|
|
|
def provider
|
|
object.seeded? ? "CDCK" : object.provider
|
|
end
|
|
end
|