mirror of
https://github.com/discourse/discourse-ai.git
synced 2025-03-09 02:40:50 +00:00
To quickly select backfill candidates without comparing SHAs, we compare the last summarized post to the topic's highest_post_number. However, hiding or deleting a post and adding a small action will update this column, causing the job to stall and re-generate the same summary repeatedly until someone posts a regular reply. On top of this, this is not always true for topics with `best_replies`, as this last reply isn't necessarily included. Since this is not evident at first glance and each summarization strategy picks its targets differently, I'm opting to simplify the backfill logic and how we track potential candidates. The first step is dropping `content_range`, which serves no purpose and it's there because summary caching was supposed to work differently at the beginning. So instead, I'm replacing it with a column called `highest_target_number`, which tracks `highest_post_number` for topics and could track other things like channel's `message_count` in the future. Now that we have this column when selecting every potential backfill candidate, we'll check if the summary is truly outdated by comparing the SHAs, and if it's not, we just update the column and move on
74 lines
2.1 KiB
Ruby
74 lines
2.1 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
class AiSummary < ActiveRecord::Base
|
|
# TODO remove this line 01-3-2025
|
|
self.ignored_columns = %i[content_range]
|
|
|
|
belongs_to :target, polymorphic: true
|
|
|
|
enum :summary_type, { complete: 0, gist: 1 }
|
|
enum :origin, { human: 0, system: 1 }
|
|
|
|
def self.store!(strategy, llm_model, summary, og_content, human:)
|
|
content_ids = og_content.map { |c| c[:id] }
|
|
|
|
AiSummary
|
|
.upsert(
|
|
{
|
|
target_id: strategy.target.id,
|
|
target_type: strategy.target.class.name,
|
|
algorithm: llm_model.name,
|
|
highest_target_number: strategy.highest_target_number,
|
|
summarized_text: summary,
|
|
original_content_sha: build_sha(content_ids.join),
|
|
summary_type: strategy.type,
|
|
origin: !!human ? origins[:human] : origins[:system],
|
|
},
|
|
unique_by: %i[target_id target_type summary_type],
|
|
update_only: %i[
|
|
summarized_text
|
|
original_content_sha
|
|
algorithm
|
|
origin
|
|
highest_target_number
|
|
],
|
|
)
|
|
.first
|
|
.then { AiSummary.find_by(id: _1["id"]) }
|
|
end
|
|
|
|
def self.build_sha(joined_ids)
|
|
Digest::SHA256.hexdigest(joined_ids)
|
|
end
|
|
|
|
def mark_as_outdated
|
|
@outdated = true
|
|
end
|
|
|
|
def outdated
|
|
@outdated || false
|
|
end
|
|
end
|
|
|
|
# == Schema Information
|
|
#
|
|
# Table name: ai_summaries
|
|
#
|
|
# id :bigint not null, primary key
|
|
# target_id :integer not null
|
|
# target_type :string not null
|
|
# summarized_text :string not null
|
|
# original_content_sha :string not null
|
|
# algorithm :string not null
|
|
# created_at :datetime not null
|
|
# updated_at :datetime not null
|
|
# summary_type :integer default("complete"), not null
|
|
# origin :integer
|
|
# highest_target_number :integer not null
|
|
#
|
|
# Indexes
|
|
#
|
|
# idx_on_target_id_target_type_summary_type_3355609fbb (target_id,target_type,summary_type) UNIQUE
|
|
# index_ai_summaries_on_target_type_and_target_id (target_type,target_id)
|
|
#
|