discourse-ai/spec/lib/modules/embeddings/semantic_related_spec.rb
Rafael dos Santos Silva 2c0f535bab
FEATURE: HyDE-powered semantic search. (#136)
* FEATURE: HyDE-powered semantic search.

It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way.

We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search.

This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying.

Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead.

* Missing translation and rate limiting

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-09-05 11:08:23 -03:00

44 lines
1.4 KiB
Ruby

# frozen_string_literal: true
require "rails_helper"
describe DiscourseAi::Embeddings::SemanticRelated do
subject(:semantic_related) { described_class.new }
fab!(:target) { Fabricate(:topic) }
fab!(:normal_topic_1) { Fabricate(:topic) }
fab!(:normal_topic_2) { Fabricate(:topic) }
fab!(:normal_topic_3) { Fabricate(:topic) }
fab!(:unlisted_topic) { Fabricate(:topic, visible: false) }
fab!(:private_topic) { Fabricate(:private_message_topic) }
fab!(:secured_category) { Fabricate(:category, read_restricted: true) }
fab!(:secured_category_topic) { Fabricate(:topic, category: secured_category) }
fab!(:closed_topic) { Fabricate(:topic, closed: true) }
before { SiteSetting.ai_embeddings_semantic_related_topics_enabled = true }
describe "#related_topic_ids_for" do
context "when embeddings do not exist" do
let (:topic) do
Fabricate(:topic).tap { described_class.clear_cache_for(target) }
end
it "queues job only once per 15 minutes" do
results = nil
expect_enqueued_with(job: :generate_embeddings, args: { topic_id: topic.id }) do
results = semantic_related.related_topic_ids_for(topic)
end
expect(results).to eq([])
expect_not_enqueued_with(job: :generate_embeddings, args: { topic_id: topic.id }) do
results = semantic_related.related_topic_ids_for(topic)
end
expect(results).to eq([])
end
end
end
end