FEATURE: PDF support for rag pipeline

.gitignore

@@ -2,3 +2,5 @@ node_modules
 /gems
 /auto_generated
 .env
+evals/log
+evals/cases

admin/assets/javascripts/discourse/routes/admin-plugins-show-discourse-ai-tools-edit.js

@@ -14,5 +14,7 @@ export default class DiscourseAiToolsEditRoute extends DiscourseRoute {
 
     controller.set("allTools", toolsModel);
     controller.set("presets", toolsModel.resultSetMeta.presets);
+    controller.set("llms", toolsModel.resultSetMeta.llms);
+    controller.set("settings", toolsModel.resultSetMeta.settings);
   }
 }

admin/assets/javascripts/discourse/routes/admin-plugins-show-discourse-ai-tools-new.js

@@ -11,5 +11,7 @@ export default class DiscourseAiToolsNewRoute extends DiscourseRoute {
 
     controller.set("allTools", toolsModel);
     controller.set("presets", toolsModel.resultSetMeta.presets);
+    controller.set("llms", toolsModel.resultSetMeta.llms);
+    controller.set("settings", toolsModel.resultSetMeta.settings);
   }
 }

admin/assets/javascripts/discourse/templates/admin-plugins/show/discourse-ai-tools/edit.hbs

@@ -3,5 +3,7 @@
     @tools={{this.allTools}}
     @model={{this.model}}
     @presets={{this.presets}}
+    @llms={{this.llms}}
+    @settings={{this.settings}}
   />
 </section>

admin/assets/javascripts/discourse/templates/admin-plugins/show/discourse-ai-tools/new.hbs

@@ -3,5 +3,7 @@
     @tools={{this.allTools}}
     @model={{this.model}}
     @presets={{this.presets}}
+    @llms={{this.llms}}
+    @settings={{this.settings}}
   />
 </section>

app/controllers/discourse_ai/admin/ai_personas_controller.rb

@@ -32,10 +32,19 @@ def index
             }
           end
         llms =
-          DiscourseAi::Configuration::LlmEnumerator
-            .values(allowed_seeded_llms: SiteSetting.ai_bot_allowed_seeded_models)
-            .map { |hash| { id: hash[:value], name: hash[:name] } }
-        render json: { ai_personas: ai_personas, meta: { tools: tools, llms: llms } }
+          DiscourseAi::Configuration::LlmEnumerator.values_for_serialization(
+            allowed_seeded_llm_ids: SiteSetting.ai_bot_allowed_seeded_models_map,
+          )
+        render json: {
+                 ai_personas: ai_personas,
+                 meta: {
+                   tools: tools,
+                   llms: llms,
+                   settings: {
+                     rag_pdf_images_enabled: SiteSetting.ai_rag_pdf_images_enabled,
+                   },
+                 },
+               }
       end
 
       def new
@@ -187,15 +196,16 @@ def ai_persona_params
             :priority,
             :top_p,
             :temperature,
-            :default_llm,
+            :default_llm_id,
             :user_id,
             :max_context_posts,
             :vision_enabled,
             :vision_max_pixels,
             :rag_chunk_tokens,
             :rag_chunk_overlap_tokens,
             :rag_conversation_chunks,
-            :question_consolidator_llm,
+            :rag_llm_model_id,
+            :question_consolidator_llm_id,
             :allow_chat_channel_mentions,
             :allow_chat_direct_messages,
             :allow_topic_mentions,

app/controllers/discourse_ai/admin/ai_tools_controller.rb

@@ -90,6 +90,7 @@ def ai_tool_params
             :summary,
             :rag_chunk_tokens,
             :rag_chunk_overlap_tokens,
+            :rag_llm_model_id,
             rag_uploads: [:id],
             parameters: [:name, :type, :description, :required, enum: []],
           )

app/controllers/discourse_ai/admin/rag_document_fragments_controller.rb

@@ -49,6 +49,7 @@ def upload_file
       def validate_extension!(filename)
         extension = File.extname(filename)[1..-1] || ""
         authorized_extensions = %w[txt md]
+        authorized_extensions.concat(%w[pdf png jpg jpeg]) if SiteSetting.ai_rag_pdf_images_enabled
         if !authorized_extensions.include?(extension)
           raise Discourse::InvalidParameters.new(
                   I18n.t(

app/jobs/regular/digest_rag_upload.rb

@@ -28,7 +28,7 @@ def execute(args)
 
       # Check if this is the first time we process this upload.
       if fragment_ids.empty?
-        document = get_uploaded_file(upload)
+        document = get_uploaded_file(upload: upload, target: target)
         return if document.nil?
 
         RagDocumentFragment.publish_status(upload, { total: 0, indexed: 0, left: 0 })
@@ -163,7 +163,38 @@ def first_chunk(text, chunk_tokens:, tokenizer:, splitters: ["\n\n", "\n", ".",
       [buffer, split_char]
     end
 
-    def get_uploaded_file(upload)
+    def get_uploaded_file(upload:, target:)
+      if %w[pdf png jpg jpeg].include?(upload.extension) && !SiteSetting.ai_rag_pdf_images_enabled
+        raise Discourse::InvalidAccess.new(
+                "The setting ai_rag_pdf_images_enabled is false, can not index images and pdfs.",
+              )
+      end
+      if upload.extension == "pdf"
+        pages =
+          DiscourseAi::Utils::PdfToImages.new(
+            upload: upload,
+            user: Discourse.system_user,
+          ).uploaded_pages
+
+        return(
+          DiscourseAi::Utils::ImageToText.as_fake_file(
+            uploads: pages,
+            llm_model: target.rag_llm_model,
+            user: Discourse.system_user,
+          )
+        )
+      end
+
+      if %w[png jpg jpeg].include?(upload.extension)
+        return(
+          DiscourseAi::Utils::ImageToText.as_fake_file(
+            uploads: [upload],
+            llm_model: target.rag_llm_model,
+            user: Discourse.system_user,
+          )
+        )
+      end
+
       store = Discourse.store
       @file ||=
         if store.external?

app/models/ai_persona.rb

@@ -1,8 +1,8 @@
 # frozen_string_literal: true
 
 class AiPersona < ActiveRecord::Base
-  # TODO remove this line 01-1-2025
-  self.ignored_columns = %i[commands allow_chat mentionable]
+  # TODO remove this line 01-10-2025
+  self.ignored_columns = %i[default_llm question_consolidator_llm]
 
   # places a hard limit, so per site we cache a maximum of 500 classes
   MAX_PERSONAS_PER_SITE = 500
@@ -12,7 +12,7 @@ class AiPersona < ActiveRecord::Base
   validates :system_prompt, presence: true, length: { maximum: 10_000_000 }
   validate :system_persona_unchangeable, on: :update, if: :system
   validate :chat_preconditions
-  validate :allowed_seeded_model, if: :default_llm
+  validate :allowed_seeded_model, if: :default_llm_id
   validates :max_context_posts, numericality: { greater_than: 0 }, allow_nil: true
   # leaves some room for growth but sets a maximum to avoid memory issues
   # we may want to revisit this in the future
@@ -30,6 +30,10 @@ class AiPersona < ActiveRecord::Base
   belongs_to :created_by, class_name: "User"
   belongs_to :user
 
+  belongs_to :default_llm, class_name: "LlmModel"
+  belongs_to :question_consolidator_llm, class_name: "LlmModel"
+  belongs_to :rag_llm_model, class_name: "LlmModel"
+
   has_many :upload_references, as: :target, dependent: :destroy
   has_many :uploads, through: :upload_references
 
@@ -62,7 +66,7 @@ def self.persona_users(user: nil)
             user_id: persona.user_id,
             username: persona.user.username_lower,
             allowed_group_ids: persona.allowed_group_ids,
-            default_llm: persona.default_llm,
+            default_llm_id: persona.default_llm_id,
             force_default_llm: persona.force_default_llm,
             allow_chat_channel_mentions: persona.allow_chat_channel_mentions,
             allow_chat_direct_messages: persona.allow_chat_direct_messages,
@@ -157,12 +161,12 @@ def class_instance
       user_id
       system
       mentionable
-      default_llm
+      default_llm_id
       max_context_posts
       vision_enabled
       vision_max_pixels
       rag_conversation_chunks
-      question_consolidator_llm
+      question_consolidator_llm_id
       allow_chat_channel_mentions
       allow_chat_direct_messages
       allow_topic_mentions
@@ -302,7 +306,7 @@ def chat_preconditions
     if (
          allow_chat_channel_mentions || allow_chat_direct_messages || allow_topic_mentions ||
            force_default_llm
-       ) && !default_llm
+       ) && !default_llm_id
       errors.add(:default_llm, I18n.t("discourse_ai.ai_bot.personas.default_llm_required"))
     end
   end
@@ -332,13 +336,12 @@ def ensure_not_system
   end
 
   def allowed_seeded_model
-    return if default_llm.blank?
+    return if default_llm_id.blank?
 
-    llm = LlmModel.find_by(id: default_llm.split(":").last.to_i)
-    return if llm.nil?
-    return if !llm.seeded?
+    return if default_llm.nil?
+    return if !default_llm.seeded?
 
-    return if SiteSetting.ai_bot_allowed_seeded_models.include?(llm.id.to_s)
+    return if SiteSetting.ai_bot_allowed_seeded_models_map.include?(default_llm.id.to_s)
 
     errors.add(:default_llm, I18n.t("discourse_ai.llm.configuration.invalid_seeded_model"))
   end
@@ -348,36 +351,37 @@ def allowed_seeded_model
 #
 # Table name: ai_personas
 #
-#  id                          :bigint           not null, primary key
-#  name                        :string(100)      not null
-#  description                 :string(2000)     not null
-#  system_prompt               :string(10000000) not null
-#  allowed_group_ids           :integer          default([]), not null, is an Array
-#  created_by_id               :integer
-#  enabled                     :boolean          default(TRUE), not null
-#  created_at                  :datetime         not null
-#  updated_at                  :datetime         not null
-#  system                      :boolean          default(FALSE), not null
-#  priority                    :boolean          default(FALSE), not null
-#  temperature                 :float
-#  top_p                       :float
-#  user_id                     :integer
-#  default_llm                 :text
-#  max_context_posts           :integer
-#  vision_enabled              :boolean          default(FALSE), not null
-#  vision_max_pixels           :integer          default(1048576), not null
-#  rag_chunk_tokens            :integer          default(374), not null
-#  rag_chunk_overlap_tokens    :integer          default(10), not null
-#  rag_conversation_chunks     :integer          default(10), not null
-#  question_consolidator_llm   :text
-#  tool_details                :boolean          default(TRUE), not null
-#  tools                       :json             not null
-#  forced_tool_count           :integer          default(-1), not null
-#  allow_chat_channel_mentions :boolean          default(FALSE), not null
-#  allow_chat_direct_messages  :boolean          default(FALSE), not null
-#  allow_topic_mentions        :boolean          default(FALSE), not null
-#  allow_personal_messages     :boolean          default(TRUE), not null
-#  force_default_llm           :boolean          default(FALSE), not null
+#  id                           :bigint           not null, primary key
+#  name                         :string(100)      not null
+#  description                  :string(2000)     not null
+#  system_prompt                :string(10000000) not null
+#  allowed_group_ids            :integer          default([]), not null, is an Array
+#  created_by_id                :integer
+#  enabled                      :boolean          default(TRUE), not null
+#  created_at                   :datetime         not null
+#  updated_at                   :datetime         not null
+#  system                       :boolean          default(FALSE), not null
+#  priority                     :boolean          default(FALSE), not null
+#  temperature                  :float
+#  top_p                        :float
+#  user_id                      :integer
+#  max_context_posts            :integer
+#  vision_enabled               :boolean          default(FALSE), not null
+#  vision_max_pixels            :integer          default(1048576), not null
+#  rag_chunk_tokens             :integer          default(374), not null
+#  rag_chunk_overlap_tokens     :integer          default(10), not null
+#  rag_conversation_chunks      :integer          default(10), not null
+#  tool_details                 :boolean          default(TRUE), not null
+#  tools                        :json             not null
+#  forced_tool_count            :integer          default(-1), not null
+#  allow_chat_channel_mentions  :boolean          default(FALSE), not null
+#  allow_chat_direct_messages   :boolean          default(FALSE), not null
+#  allow_topic_mentions         :boolean          default(FALSE), not null
+#  allow_personal_messages      :boolean          default(TRUE), not null
+#  force_default_llm            :boolean          default(FALSE), not null
+#  rag_llm_model_id             :bigint
+#  default_llm_id               :bigint
+#  question_consolidator_llm_id :bigint
 #
 # Indexes
 #

app/models/ai_tool.rb

@@ -8,6 +8,7 @@ class AiTool < ActiveRecord::Base
   validates :script, presence: true, length: { maximum: 100_000 }
   validates :created_by_id, presence: true
   belongs_to :created_by, class_name: "User"
+  belongs_to :rag_llm_model, class_name: "LlmModel"
   has_many :rag_document_fragments, dependent: :destroy, as: :target
   has_many :upload_references, as: :target, dependent: :destroy
   has_many :uploads, through: :upload_references
@@ -371,4 +372,4 @@ def self.presets
 #  rag_chunk_tokens         :integer          default(374), not null
 #  rag_chunk_overlap_tokens :integer          default(10), not null
 #  tool_name                :string(100)      default(""), not null
-#
+#  rag_llm_model_id         :bigint

app/models/llm_model.rb

@@ -70,7 +70,7 @@ def self.provider_params
   end
 
   def to_llm
-    DiscourseAi::Completions::Llm.proxy(identifier)
+    DiscourseAi::Completions::Llm.proxy(self)
   end
 
   def identifier

app/serializers/ai_custom_tool_list_serializer.rb

@@ -6,7 +6,13 @@ class AiCustomToolListSerializer < ApplicationSerializer
   has_many :ai_tools, serializer: AiCustomToolSerializer, embed: :objects
 
   def meta
-    { presets: AiTool.presets }
+    {
+      presets: AiTool.presets,
+      llms: DiscourseAi::Configuration::LlmEnumerator.values_for_serialization,
+      settings: {
+        rag_pdf_images_enabled: SiteSetting.ai_rag_pdf_images_enabled,
+      },
+    }
   end
 
   def ai_tools

app/serializers/ai_custom_tool_serializer.rb

@@ -10,6 +10,7 @@ class AiCustomToolSerializer < ApplicationSerializer
              :script,
              :rag_chunk_tokens,
              :rag_chunk_overlap_tokens,
+             :rag_llm_model_id,
              :created_by_id,
              :created_at,
              :updated_at

app/serializers/localized_ai_persona_serializer.rb

@@ -14,15 +14,16 @@ class LocalizedAiPersonaSerializer < ApplicationSerializer
              :allowed_group_ids,
              :temperature,
              :top_p,
-             :default_llm,
+             :default_llm_id,
              :user_id,
              :max_context_posts,
              :vision_enabled,
              :vision_max_pixels,
              :rag_chunk_tokens,
              :rag_chunk_overlap_tokens,
              :rag_conversation_chunks,
-             :question_consolidator_llm,
+             :rag_llm_model_id,
+             :question_consolidator_llm_id,
              :tool_details,
              :forced_tool_count,
              :allow_chat_channel_mentions,