FIX: Use specific prompts for topic titles (#252)

This commit forks the existing DiscourseAi translator into a PostTranslator and TopicTranslator, with varying prompts to cater for the different content that can occur in post raw and topic titles.

We need to do this as titles tend to have a lot of text, and not have html or markdown, and the existing post content prompts are causing AI to pad the titles with html that does not exist.

This commit also improves the prompts for both types.

Author: nattsw

app/services/discourse_ai/base_translator.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+module DiscourseAi
+  class BaseTranslator
+    def initialize(text, target_language)
+      @text = text
+      @target_language = target_language
+    end
+
+    def translate
+      prompt =
+        DiscourseAi::Completions::Prompt.new(
+          build_prompt(@target_language),
+          messages: [{ type: :user, content: "#{@text}", id: "user" }],
+        )
+
+      DiscourseAi::Completions::Llm.proxy(SiteSetting.ai_helper_model).generate(
+        prompt,
+        user: Discourse.system_user,
+        feature_name: "translator-translate",
+      )
+    end
+
+    private
+
+    def build_prompt(target_language)
+      prompt_template % { target_language: target_language }
+    end
+
+    def prompt_template
+      raise NotImplementedError
+    end
+  end
+end

app/services/discourse_ai/post_translator.rb

@@ -0,0 +1,22 @@
+# frozen_string_literal: true
+
+module DiscourseAi
+  class PostTranslator < BaseTranslator
+    PROMPT_TEMPLATE = <<~TEXT.freeze
+      Translate this content to "%{target_language}". You must:
+      1. Translate the content accurately while preserving any Markdown, HTML elements, or newlines
+      2. Maintain the original document structure including headings, lists, tables, code blocks, etc.
+      3. Preserve all links, images, and other media references without translation
+      4. Handle code snippets appropriately - don't translate variable names, functions, or syntax within code blocks (```), but translate comments
+      5. When encountering technical terminology, provide the accepted target language term if it exists, or transliterate if no equivalent exists, with the original term in parentheses
+      6. For ambiguous terms or phrases, choose the most contextually appropriate translation
+      7. Do not add any content besides the translation
+      8. The translation must not have other languages other than the original and the target language
+      9. You are being consumed via an API, only EVER return the translated text, do not return any other information
+    TEXT
+
+    private def prompt_template
+      PROMPT_TEMPLATE
+    end
+  end
+end

app/services/discourse_ai/topic_translator.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+
+module DiscourseAi
+  class TopicTranslator < BaseTranslator
+    PROMPT_TEMPLATE = <<~TEXT.freeze
+      Translate this topic title to "%{target_language}"
+      - Keep the original language when it is a proper noun or technical term
+      - The translation should be around the same length as the original
+      TEXT
+
+    private def prompt_template
+      PROMPT_TEMPLATE
+    end
+  end
+end

app/services/discourse_ai/translator.rb

@@ -33,11 +33,19 @@ def self.translate!(translatable, target_locale_sym = I18n.locale)
                 ),
               )
       end
+
+      language = get_language_name(target_locale_sym)
       translated =
-        ::DiscourseAi::Translator.new(
-          text_for_translation(translatable, raw: true),
-          target_locale_sym,
-        ).translate
+        case translatable.class.name
+        when "Post"
+          ::DiscourseAi::PostTranslator.new(
+            text_for_translation(translatable, raw: true),
+            language,
+          ).translate
+        when "Topic"
+          ::DiscourseAi::TopicTranslator.new(text_for_translation(translatable), language).translate
+        end
+
       DiscourseTranslator::TranslatedContentNormalizer.normalize(translatable, translated)
     end
 
@@ -47,5 +55,10 @@ def self.required_settings_enabled
       SiteSetting.translator_enabled && SiteSetting.translator_provider == "DiscourseAi" &&
         SiteSetting.discourse_ai_enabled && SiteSetting.ai_helper_enabled
     end
+
+    def self.get_language_name(target_locale_sym)
+      LocaleSiteSetting.language_names.dig(target_locale_sym.to_s, "name") ||
+        "locale \"#{target_locale_sym}\""
+    end
   end
 end

app/services/discourse_translator/discourse_ai.rb

@@ -2,7 +2,7 @@
 
 require "rails_helper"
 
-describe DiscourseAi::Translator do
+describe DiscourseAi::BaseTranslator do
   before do
     Fabricate(:fake_model).tap do |fake_llm|
       SiteSetting.public_send("ai_helper_model=", "custom:#{fake_llm.id}")
@@ -17,19 +17,21 @@
     it "creates the correct prompt" do
       allow(DiscourseAi::Completions::Prompt).to receive(:new).with(
         <<~TEXT,
-      You are an expert translator specializing in converting Markdown content from any source language to target locale "de". Your task is to:
-      1. Translate the content accurately while preserving all Markdown formatting elements
+      Translate this content to "de". You must:
+      1. Translate the content accurately while preserving any Markdown, HTML elements, or newlines
       2. Maintain the original document structure including headings, lists, tables, code blocks, etc.
       3. Preserve all links, images, and other media references without translation
       4. Handle code snippets appropriately - don't translate variable names, functions, or syntax within code blocks (```), but translate comments
       5. When encountering technical terminology, provide the accepted target language term if it exists, or transliterate if no equivalent exists, with the original term in parentheses
       6. For ambiguous terms or phrases, choose the most contextually appropriate translation
-      7. You are being consumed via an API, only EVER return the translated text, do not return any other information
+      7. Do not add any content besides the translation
+      8. The translation must not have other languages other than the original and the target language
+      9. You are being consumed via an API, only EVER return the translated text, do not return any other information
         TEXT
         messages: [{ type: :user, content: "cats are great", id: "user" }],
       ).and_call_original
 
-      described_class.new(text_to_translate, target_language).translate
+      DiscourseAi::PostTranslator.new(text_to_translate, target_language).translate
     end
 
     it "sends the translation prompt to the selected ai helper model" do
@@ -46,13 +48,13 @@
         feature_name: "translator-translate",
       )
 
-      described_class.new(text_to_translate, target_language).translate
+      DiscourseAi::PostTranslator.new(text_to_translate, target_language).translate
     end
 
     it "returns the translation from the llm's response" do
       DiscourseAi::Completions::Llm.with_prepared_responses(["hur dur hur dur!"]) do
         expect(
-          described_class.new(text_to_translate, target_language).translate,
+          DiscourseAi::PostTranslator.new(text_to_translate, target_language).translate,
         ).to eq "hur dur hur dur!"
       end
     end

spec/services/discourse_ai/translator_spec.rb renamed to spec/services/discourse_ai/base_translator_spec.rb

@@ -1,9 +1,8 @@
 # frozen_string_literal: true
 
-require "rails_helper"
-
 describe DiscourseTranslator::DiscourseAi do
   fab!(:post)
+  fab!(:topic)
 
   before do
     Fabricate(:fake_model).tap do |fake_llm|
@@ -36,7 +35,10 @@
   end
 
   describe ".translate" do
-    before { post.set_detected_locale("de") }
+    before do
+      post.set_detected_locale("de")
+      topic.set_detected_locale("de")
+    end
 
     it "translates the post and returns [locale, translated_text]" do
       DiscourseAi::Completions::Llm.with_prepared_responses(["some translated text"]) do
@@ -45,5 +47,14 @@
         expect(translated_text).to eq "<p>some translated text</p>"
       end
     end
+
+    it "translates the topic" do
+      allow(::DiscourseAi::TopicTranslator).to receive(:new).and_call_original
+      DiscourseAi::Completions::Llm.with_prepared_responses(["some translated text"]) do
+        locale, translated_text = DiscourseTranslator::DiscourseAi.translate(topic)
+        expect(locale).to eq "de"
+        expect(translated_text).to eq "some translated text"
+      end
+    end
   end
 end