mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-03-07 01:39:54 +00:00
6ddc17fd61
Previous to this change we relied on explicit loading for a files in Discourse AI. This had a few downsides: - Busywork whenever you add a file (an extra require relative) - We were not keeping to conventions internally ... some places were OpenAI others are OpenAi - Autoloader did not work which lead to lots of full application broken reloads when developing. This moves all of DiscourseAI into a Zeitwerk compatible structure. It also leaves some minimal amount of manual loading (automation - which is loading into an existing namespace that may or may not be there) To avoid needing /lib/discourse_ai/... we mount a namespace thus we are able to keep /lib pointed at ::DiscourseAi Various files were renamed to get around zeitwerk rules and minimize usage of custom inflections Though we can get custom inflections to work it is not worth it, will require a Discourse core patch which means we create a hard dependency.
70 lines
2.0 KiB
Ruby
70 lines
2.0 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
module Jobs
|
|
class EmbeddingsBackfill < ::Jobs::Scheduled
|
|
every 15.minutes
|
|
sidekiq_options queue: "low"
|
|
cluster_concurrency 1
|
|
|
|
def execute(args)
|
|
return unless SiteSetting.ai_embeddings_enabled
|
|
|
|
limit = SiteSetting.ai_embeddings_backfill_batch_size
|
|
rebaked = 0
|
|
|
|
strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
|
|
vector_rep =
|
|
DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
|
|
table_name = vector_rep.table_name
|
|
|
|
topics =
|
|
Topic
|
|
.joins("LEFT JOIN #{table_name} ON #{table_name}.topic_id = topics.id")
|
|
.where(archetype: Archetype.default)
|
|
.where(deleted_at: nil)
|
|
.limit(limit - rebaked)
|
|
|
|
# First, we'll try to backfill embeddings for topics that have none
|
|
topics
|
|
.where("#{table_name}.topic_id IS NULL")
|
|
.find_each do |t|
|
|
vector_rep.generate_topic_representation_from(t)
|
|
rebaked += 1
|
|
end
|
|
|
|
vector_rep.consider_indexing
|
|
|
|
return if rebaked >= limit
|
|
|
|
# Then, we'll try to backfill embeddings for topics that have outdated
|
|
# embeddings, be it model or strategy version
|
|
topics
|
|
.where(<<~SQL)
|
|
#{table_name}.model_version < #{vector_rep.version}
|
|
OR
|
|
#{table_name}.strategy_version < #{strategy.version}
|
|
SQL
|
|
.find_each do |t|
|
|
vector_rep.generate_topic_representation_from(t)
|
|
rebaked += 1
|
|
end
|
|
|
|
return if rebaked >= limit
|
|
|
|
# Finally, we'll try to backfill embeddings for topics that have outdated
|
|
# embeddings due to edits or new replies. Here we only do 10% of the limit
|
|
topics
|
|
.where("#{table_name}.updated_at < ?", 7.days.ago)
|
|
.order("random()")
|
|
.limit((limit - rebaked) / 10)
|
|
.pluck(:id)
|
|
.each do |id|
|
|
vector_rep.generate_topic_representation_from(Topic.find_by(id: id))
|
|
rebaked += 1
|
|
end
|
|
|
|
rebaked
|
|
end
|
|
end
|
|
end
|