discourse-ai/spec/lib/modules/embeddings/entry_point_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

32 lines
846 B
Ruby

# frozen_string_literal: true
require "rails_helper"
describe DiscourseAi::Embeddings::EntryPoint do
fab!(:user) { Fabricate(:user) }
describe "registering event callbacks" do
context "when creating a topic" do
let(:creator) do
PostCreator.new(
user,
raw: "this is the new content for my topic",
title: "this is my new topic title",
)
end
it "queues a job on create if embeddings is enabled" do
SiteSetting.ai_embeddings_enabled = true
expect { creator.create }.to change(Jobs::GenerateEmbeddings.jobs, :size).by(1)
end
it "does nothing if sentiment analysis is disabled" do
SiteSetting.ai_embeddings_enabled = false
expect { creator.create }.not_to change(Jobs::GenerateEmbeddings.jobs, :size)
end
end
end
end