discourse-ai/spec/requests/topic_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

41 lines
1.1 KiB
Ruby

# frozen_string_literal: true
require "rails_helper"
describe ::TopicsController do
fab!(:topic) { Fabricate(:topic) }
fab!(:topic1) { Fabricate(:topic) }
fab!(:topic2) { Fabricate(:topic) }
fab!(:topic3) { Fabricate(:topic) }
fab!(:user) { Fabricate(:admin) }
before do
SiteSetting.ai_embeddings_semantic_related_topics_enabled = true
SiteSetting.ai_embeddings_semantic_related_topics = 2
end
context "when a user is logged on" do
it "includes related topics in payload when configured" do
DiscourseAi::Embeddings::SemanticRelated
.any_instance
.stubs(:related_topic_ids_for)
.returns([topic1.id, topic2.id, topic3.id])
get("#{topic.relative_url}.json")
expect(response.status).to eq(200)
json = response.parsed_body
expect(json["suggested_topics"].length).to eq(0)
expect(json["related_topics"].length).to eq(2)
sign_in(user)
get("#{topic.relative_url}.json")
json = response.parsed_body
expect(json["suggested_topics"].length).to eq(0)
expect(json["related_topics"].length).to eq(2)
end
end
end