FIX: Add workaround to pgvector HNSW search limitations (#1133)

From [pgvector/pgvector](https://github.com/pgvector/pgvector) README

> With approximate indexes, filtering is applied after the index is scanned. If a condition matches 10% of rows, with HNSW and the default hnsw.ef_search of 40, only 4 rows will match on average. For more rows, increase hnsw.ef_search.
> 
> Starting with 0.8.0, you can enable [iterative index scans](https://github.com/pgvector/pgvector#iterative-index-scans), which will automatically scan more of the index when needed.


Since we are stuck on 0.7.0 we are going the first option for now.

lib/ai_helper/semantic_categorizer.rb

@@ -5,13 +5,15 @@ module DiscourseAi
       def initialize(input, user)
         @user = user
         @text = input[:text]
+        @vector = DiscourseAi::Embeddings::Vector.instance
+        @schema = DiscourseAi::Embeddings::Schema.for(Topic)
       end
 
       def categories
         return [] if @text.blank?
         return [] if !DiscourseAi::Embeddings.enabled?
 
-        candidates = nearest_neighbors(limit: 100)
+        candidates = nearest_neighbors
         return [] if candidates.empty?
 
         candidate_ids = candidates.map(&:first)
@@ -40,6 +42,9 @@ module DiscourseAi
             }
           end
           .map do |c|
+            # Note: <#> returns the negative inner product since Postgres only supports ASC order index scans on operators
+            c[:score] = (c[:score] + 1).abs if @vector.vdef.pg_function = "<#>"
+
             c[:score] = 1 / (c[:score] + 1) # inverse of the distance
             c
           end
@@ -72,6 +77,9 @@ module DiscourseAi
           .with_index { |tag_list, index| { tags: tag_list, score: candidates[index].last } }
           .flat_map { |c| c[:tags].map { |t| { name: t, score: c[:score] } } }
           .map do |c|
+            # Note: <#> returns the negative inner product since Postgres only supports ASC order index scans on operators
+            c[:score] = (c[:score] + 1).abs if @vector.vdef.pg_function = "<#>"
+
             c[:score] = 1 / (c[:score] + 1) # inverse of the distance
             c
           end
@@ -91,11 +99,8 @@ module DiscourseAi
 
       private
 
-      def nearest_neighbors(limit: 100)
+      def nearest_neighbors(limit: 50)
-        vector = DiscourseAi::Embeddings::Vector.instance
+        raw_vector = @vector.vector_from(@text)
-        schema = DiscourseAi::Embeddings::Schema.for(Topic)
-
-        raw_vector = vector.vector_from(@text)
 
         muted_category_ids = nil
         if @user.present?
@@ -106,7 +111,7 @@ module DiscourseAi
             ).pluck(:category_id)
         end
 
-        schema
+        @schema
           .asymmetric_similarity_search(raw_vector, limit: limit, offset: 0) do |builder|
             builder.join("topics t on t.id = topic_id")
             unless muted_category_ids.empty?

lib/embeddings/schema.rb

@@ -15,6 +15,8 @@ module DiscourseAi
       EMBEDDING_TARGETS = %w[topics posts document_fragments]
       EMBEDDING_TABLES = [TOPICS_TABLE, POSTS_TABLE, RAG_DOCS_TABLE]
 
+      DEFAULT_HNSW_EF_SEARCH = 40
+
       MissingEmbeddingError = Class.new(StandardError)
 
       class << self
@@ -132,6 +134,8 @@ module DiscourseAi
       end
 
       def asymmetric_similarity_search(embedding, limit:, offset:)
+        before_query = hnsw_search_workaround(limit)
+
         builder = DB.build(<<~SQL)
           WITH candidates AS (
             SELECT
@@ -153,7 +157,7 @@ module DiscourseAi
           ORDER BY
             embeddings::halfvec(#{dimensions}) #{pg_function} '[:query_embedding]'::halfvec(#{dimensions})
           LIMIT :limit
-          OFFSET :offset
+          OFFSET :offset;
         SQL
 
         builder.where(
@@ -171,18 +175,24 @@ module DiscourseAi
           candidates_limit = limit * 2
         end
 
+        ActiveRecord::Base.transaction do
+          DB.exec(before_query) if before_query.present?
           builder.query(
             query_embedding: embedding,
             candidates_limit: candidates_limit,
             limit: limit,
             offset: offset,
           )
+        end
       rescue PG::Error => e
         Rails.logger.error("Error #{e} querying embeddings for model #{vector_def.display_name}")
         raise MissingEmbeddingError
       end
 
       def symmetric_similarity_search(record)
+        limit = 200
+        before_query = hnsw_search_workaround(limit)
+
         builder = DB.build(<<~SQL)
           WITH le_target AS (
             SELECT
@@ -210,7 +220,7 @@ module DiscourseAi
                   le_target
                 LIMIT 1
               )
-            LIMIT 200
+            LIMIT #{limit}
           ) AS widenet
           ORDER BY
             embeddings::halfvec(#{dimensions}) #{pg_function} (
@@ -220,14 +230,17 @@ module DiscourseAi
                 le_target
               LIMIT 1
             )
-          LIMIT 100;
+          LIMIT #{limit / 2};
         SQL
 
         builder.where("model_id = :vid AND strategy_id = :vsid")
 
         yield(builder) if block_given?
 
+        ActiveRecord::Base.transaction do
+          DB.exec(before_query) if before_query.present?
           builder.query(vid: vector_def.id, vsid: vector_def.strategy_id, target_id: record.id)
+        end
       rescue PG::Error => e
         Rails.logger.error("Error #{e} querying embeddings for model #{vector_def.display_name}")
         raise MissingEmbeddingError
@@ -259,6 +272,13 @@ module DiscourseAi
 
       private
 
+      def hnsw_search_workaround(limit)
+        threshold = limit * 2
+
+        return "" if threshold < DEFAULT_HNSW_EF_SEARCH
+        "SET LOCAL hnsw.ef_search = #{threshold};"
+      end
+
       delegate :dimensions, :pg_function, to: :vector_def
     end
   end

spec/system/ai_helper/ai_composer_helper_spec.rb

@@ -3,6 +3,7 @@
 RSpec.describe "AI Composer helper", type: :system, js: true do
   fab!(:user) { Fabricate(:admin, refresh_auto_groups: true) }
   fab!(:non_member_group) { Fabricate(:group) }
+  fab!(:embedding_definition)
 
   before do
     Group.find_by(id: Group::AUTO_GROUPS[:admins]).add(user)
@@ -243,7 +244,10 @@ RSpec.describe "AI Composer helper", type: :system, js: true do
   end
 
   context "when suggesting the category with AI category suggester" do
-    before { SiteSetting.ai_embeddings_enabled = true }
+    before do
+      SiteSetting.ai_embeddings_selected_model = embedding_definition.id
+      SiteSetting.ai_embeddings_enabled = true
+    end
 
     it "updates the category with the suggested category" do
       response =
@@ -274,7 +278,10 @@ RSpec.describe "AI Composer helper", type: :system, js: true do
   end
 
   context "when suggesting the tags with AI tag suggester" do
-    before { SiteSetting.ai_embeddings_enabled = true }
+    before do
+      SiteSetting.ai_embeddings_selected_model = embedding_definition.id
+      SiteSetting.ai_embeddings_enabled = true
+    end
 
     it "updates the tag with the suggested tag" do
       response =

spec/system/ai_helper/ai_split_topic_suggestion_spec.rb

@@ -35,6 +35,7 @@ RSpec.describe "AI Post helper", type: :system, js: true do
   fab!(:cloud) { Fabricate(:tag) }
   fab!(:feedback) { Fabricate(:tag) }
   fab!(:review) { Fabricate(:tag) }
+  fab!(:embedding_definition)
 
   before do
     Group.find_by(id: Group::AUTO_GROUPS[:admins]).add(user)
@@ -80,7 +81,10 @@ RSpec.describe "AI Post helper", type: :system, js: true do
     end
 
     context "when suggesting categories with AI category suggester" do
-      before { SiteSetting.ai_embeddings_enabled = true }
+      before do
+        SiteSetting.ai_embeddings_selected_model = embedding_definition.id
+        SiteSetting.ai_embeddings_enabled = true
+      end
 
       skip "TODO: Category suggester only loading one category in test" do
         it "updates the category with the suggested category" do
@@ -108,7 +112,10 @@ RSpec.describe "AI Post helper", type: :system, js: true do
     end
 
     context "when suggesting tags with AI tag suggester" do
-      before { SiteSetting.ai_embeddings_enabled = true }
+      before do
+        SiteSetting.ai_embeddings_selected_model = embedding_definition.id
+        SiteSetting.ai_embeddings_enabled = true
+      end
 
       it "update the tag with the suggested tag" do
         response =