discourse · xfalcox · Jun 2, 2025 · May 8, 2025 · May 9, 2025 · May 9, 2025
diff --git a/app/jobs/regular/generate_inferred_concepts.rb b/app/jobs/regular/generate_inferred_concepts.rb
@@ -0,0 +1,70 @@
+# frozen_string_literal: true
+
+module Jobs
+  class GenerateInferredConcepts < ::Jobs::Base
+    sidekiq_options queue: "low"
+
+    # Process items to generate new concepts
+    #
+    # @param args [Hash] Contains job arguments
+    # @option args [String] :item_type Required - Type of items to process ('topics' or 'posts')
+    # @option args [Array<Integer>] :item_ids Required - List of item IDs to process
+    # @option args [Integer] :batch_size (100) Number of items to process in each batch
+    # @option args [Boolean] :match_only (false) Only match against existing concepts without generating new ones
+    def execute(args = {})
+      return if args[:item_ids].blank? || args[:item_type].blank?
+
+      if %w[topics posts].exclude?(args[:item_type])
+        Rails.logger.error("Invalid item_type for GenerateInferredConcepts: #{args[:item_type]}")
+        return
+      end
+
+      # Process items in smaller batches to avoid memory issues
+      batch_size = args[:batch_size] || 100
+
+      # Get the list of item IDs
+      item_ids = args[:item_ids]
+      match_only = args[:match_only] || false
+
+      # Process items in batches
+      item_ids.each_slice(batch_size) do |batch_item_ids|
+        process_batch(batch_item_ids, args[:item_type], match_only)
+      end
+    end
+
+    private
+
+    def process_batch(item_ids, item_type, match_only)
+      klass = item_type.singularize.classify.constantize
+      items = klass.where(id: item_ids)
+      manager = DiscourseAi::InferredConcepts::Manager.new
+
+      items.each do |item|
+        begin
+          process_item(item, item_type, match_only, manager)
+        rescue => e
+          Rails.logger.error(
+            "Error generating concepts from #{item_type.singularize} #{item.id}: #{e.message}\n#{e.backtrace.join("\n")}",
+          )
+        end
+      end
+    end
+
+    def process_item(item, item_type, match_only, manager)
+      # Use the Manager method that handles both identifying and creating concepts
+      if match_only
+        if item_type == "topics"
+          manager.match_topic_to_concepts(item)
+        else # posts
+          manager.match_post_to_concepts(item)
+        end
+      else
+        if item_type == "topics"
+          manager.generate_concepts_from_topic(item)
+        else # posts
+          manager.generate_concepts_from_post(item)
+        end
+      end
+    end
+  end
+end
diff --git a/app/jobs/scheduled/generate_concepts_from_popular_items.rb b/app/jobs/scheduled/generate_concepts_from_popular_items.rb
@@ -0,0 +1,87 @@
+# frozen_string_literal: true
+
+module Jobs
+  class GenerateConceptsFromPopularItems < ::Jobs::Scheduled
+    every 1.day
+
+    # This job runs daily and generates new concepts from popular topics and posts
+    # It selects items based on engagement metrics and generates concepts from their content
+    def execute(_args)
+      return unless SiteSetting.inferred_concepts_enabled
+
+      process_popular_topics
+      process_popular_posts
+    end
+
+    private
+
+    def process_popular_topics
+      # Find candidate topics that are popular and don't have concepts yet
+      manager = DiscourseAi::InferredConcepts::Manager.new
+      candidates =
+        manager.find_candidate_topics(
+          limit: SiteSetting.inferred_concepts_daily_topics_limit || 20,
+          min_posts: SiteSetting.inferred_concepts_min_posts || 5,
+          min_likes: SiteSetting.inferred_concepts_min_likes || 10,
+          min_views: SiteSetting.inferred_concepts_min_views || 100,
+          created_after: SiteSetting.inferred_concepts_lookback_days.days.ago,
+        )
+
+      return if candidates.blank?
+
+      # Process candidate topics - first generate concepts, then match
+      Jobs.enqueue(
+        :generate_inferred_concepts,
+        item_type: "topics",
+        item_ids: candidates.map(&:id),
+        batch_size: 10,
+      )
+
+      if SiteSetting.inferred_concepts_background_match
+        # Schedule a follow-up job to match existing concepts
+        Jobs.enqueue_in(
+          1.hour,
+          :generate_inferred_concepts,
+          item_type: "topics",
+          item_ids: candidates.map(&:id),
+          batch_size: 10,
+          match_only: true,
+        )
+      end
+    end
+
+    def process_popular_posts
+      # Find candidate posts that are popular and don't have concepts yet
+      manager = DiscourseAi::InferredConcepts::Manager.new
+      candidates =
+        manager.find_candidate_posts(
+          limit: SiteSetting.inferred_concepts_daily_posts_limit || 30,
+          min_likes: SiteSetting.inferred_concepts_post_min_likes || 5,
+          exclude_first_posts: true,
+          created_after: SiteSetting.inferred_concepts_lookback_days.days.ago,
+        )
+
+      return if candidates.blank?
+
+      # Process candidate posts - first generate concepts, then match
+      Jobs.enqueue(
+        :generate_inferred_concepts,
+        item_type: "posts",
+        item_ids: candidates.map(&:id),
+        batch_size: 10,
+      )
+
+      if SiteSetting.inferred_concepts_background_match
+        # Schedule a follow-up job to match against existing concepts
+        Jobs.enqueue_in(
+          1.hour,
+          :generate_inferred_concepts,
+          item_type: "posts",
+          item_ids: candidates.map(&:id),
+          batch_size: 10,
+          match_only: true,
+        )
+      end
+    end
+  end
+end
diff --git a/app/models/inferred_concept.rb b/app/models/inferred_concept.rb
@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+class InferredConcept < ActiveRecord::Base
+  has_many :inferred_concept_topics
+  has_many :topics, through: :inferred_concept_topics
+
+  has_many :inferred_concept_posts
+  has_many :posts, through: :inferred_concept_posts
+
+  validates :name, presence: true, uniqueness: true
+end
+
+# == Schema Information
+#
+# Table name: inferred_concepts
+#
+#  id         :bigint           not null, primary key
+#  name       :string           not null
+#  created_at :datetime         not null
+#  updated_at :datetime         not null
+#
+# Indexes
+#
+#  index_inferred_concepts_on_name  (name) UNIQUE
+#
diff --git a/app/models/inferred_concept_post.rb b/app/models/inferred_concept_post.rb
@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+class InferredConceptPost < ActiveRecord::Base
+  belongs_to :inferred_concept
+  belongs_to :post
+
+  validates :inferred_concept_id, presence: true
+  validates :post_id, presence: true
+  validates :inferred_concept_id, uniqueness: { scope: :post_id }
+end
+
+# == Schema Information
+#
+# Table name: inferred_concept_posts
+#
+#  inferred_concept_id :bigint
+#  post_id             :bigint
+#  created_at          :datetime         not null
+#  updated_at          :datetime         not null
+#
+# Indexes
+#
+#  index_inferred_concept_posts_on_inferred_concept_id  (inferred_concept_id)
+#  index_inferred_concept_posts_uniqueness              (post_id,inferred_concept_id) UNIQUE
+#
diff --git a/app/models/inferred_concept_topic.rb b/app/models/inferred_concept_topic.rb
@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+class InferredConceptTopic < ActiveRecord::Base
+  belongs_to :inferred_concept
+  belongs_to :topic
+
+  validates :inferred_concept_id, presence: true
+  validates :topic_id, presence: true
+  validates :inferred_concept_id, uniqueness: { scope: :topic_id }
+end
+
+# == Schema Information
+#
+# Table name: inferred_concept_topics
+#
+#  inferred_concept_id :bigint
+#  topic_id            :bigint
+#  created_at          :datetime         not null
+#  updated_at          :datetime         not null
+#
+# Indexes
+#
+#  index_inferred_concept_topics_on_inferred_concept_id  (inferred_concept_id)
+#  index_inferred_concept_topics_uniqueness              (topic_id,inferred_concept_id) UNIQUE
+#
diff --git a/app/serializers/ai_inferred_concept_post_serializer.rb b/app/serializers/ai_inferred_concept_post_serializer.rb
@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+class AiInferredConceptPostSerializer < ApplicationSerializer
+  attributes :id,
+             :post_number,
+             :topic_id,
+             :topic_title,
+             :username,
+             :avatar_template,
+             :created_at,
+             :updated_at,
+             :excerpt,
+             :truncated,
+             :inferred_concepts
+
+  def avatar_template
+    User.avatar_template(object.username, object.uploaded_avatar_id)
+  end
+
+  def excerpt
+    Post.excerpt(object.cooked)
+  end
+
+  def truncated
+    object.cooked.length > SiteSetting.post_excerpt_maxlength
+  end
+
+  def inferred_concepts
+    ActiveModel::ArraySerializer.new(
+      object.inferred_concepts,
+      each_serializer: InferredConceptSerializer,
+    )
+  end
+end
diff --git a/app/serializers/inferred_concept_serializer.rb b/app/serializers/inferred_concept_serializer.rb
@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+class InferredConceptSerializer < ApplicationSerializer
+  attributes :id, :name, :created_at, :updated_at
+end
diff --git a/assets/javascripts/discourse/components/modal/ai-persona-response-format-editor.gjs b/assets/javascripts/discourse/components/modal/ai-persona-response-format-editor.gjs
@@ -22,10 +22,20 @@ export default class AiPersonaResponseFormatEditor extends Component {
           type: "string",
         },
         type: {
+          type: "string",
+          enum: ["string", "integer", "boolean", "array"],
+        },
+        array_type: {
           type: "string",
           enum: ["string", "integer", "boolean"],
+          options: {
+            dependencies: {
+              type: "array",
+            },
+          },
         },
       },
+      required: ["key", "type"],
     },
   };
 
@@ -41,7 +51,11 @@ export default class AiPersonaResponseFormatEditor extends Component {
     const toDisplay = {};
 
     this.args.data.response_format.forEach((keyDesc) => {
-      toDisplay[keyDesc.key] = keyDesc.type;
+      if (keyDesc.type === "array") {
+        toDisplay[keyDesc.key] = `[${keyDesc.array_type}]`;
+      } else {
+        toDisplay[keyDesc.key] = keyDesc.type;
+      }
     });
 
     return prettyJSON(toDisplay);

diff --git a/config/locales/server.en.yml b/config/locales/server.en.yml
@@ -330,6 +330,15 @@ en:
         short_summarizer:
           name: "Summarizer (short form)"
           description: "Default persona used to power AI short summaries for topic lists' items"
+        concept_finder:
+          name: "Concept Finder"
+          description: "AI Bot specialized in identifying concepts and themes in content"
+        concept_matcher:
+          name: "Concept Matcher"
+          description: "AI Bot specialized in matching content against existing concepts"
+        concept_deduplicator:
+          name: "Concept Deduplicator"
+          description: "AI Bot specialized in deduplicating concepts"
       topic_not_found: "Summary unavailable, topic not found!"
       summarizing: "Summarizing topic"
       searching: "Searching for: '%{query}'"
@@ -549,6 +558,9 @@ en:
       discord_search:
         name: "Discord Search"
         description: "Adds the ability to search Discord channels"
+      inferred_concepts:
+        name: "Inferred Concepts"
+        description: "Classifies topics and posts into areas of interest / labels."
 
     errors:
       quota_exceeded: "You have exceeded the quota for this model. Please try again in %{relative_time}."

diff --git a/config/settings.yml b/config/settings.yml
@@ -417,3 +417,55 @@ discourse_ai:
     default: false
     client: false
     hidden: true
+
+  inferred_concepts_enabled:
+    default: false
+    client: true
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_background_match:
+    default: false
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_daily_topics_limit:
+    default: 20
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_min_posts:
+    default: 5
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_min_likes:
+    default: 10
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_min_views:
+    default: 100
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_lookback_days:
+    default: 30
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_daily_posts_limit:
+    default: 30
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_post_min_likes:
+    default: 5
+    client: false
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_generate_persona:
+    default: "-15"
+    type: enum
+    enum: "DiscourseAi::Configuration::PersonaEnumerator"
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_match_persona:
+    default: "-16"
+    type: enum
+    enum: "DiscourseAi::Configuration::PersonaEnumerator"
+    area: "ai-features/inferred_concepts"
+  inferred_concepts_deduplicate_persona:
+    default: "-17"
+    type: enum
+    enum: "DiscourseAi::Configuration::PersonaEnumerator"
+    area: "ai-features/inferred_concepts"