Customizando o AI summarizer para usar outros idiomas

Olá, eu uso localmente google/gemma-3-4b com a versão mais recente do Discourse. O modelo atende bem a alguns idiomas. Quando testo usando API ou LM Studio, ele fornece o resumo no idioma que eu peço.

O Discourse sempre resume em inglês no momento. As etapas abaixo descrevem como codificar permanentemente o idioma de sumarização (não inglês).


Importante! Suas alterações serão perdidas na próxima reconstrução.

As linhas codificadas permanentemente estão abaixo em dois arquivos. Os valores do banco de dados da tabela ai_personas não são usados (julho de 2025). Para aqueles que brincam com ambientes não de produção, você pode codificar permanentemente seu idioma nativo:

  1. Conecte-se via SSH ao seu servidor.

  2. Copie o arquivo codificado permanentemente summarize.rb do contêiner para o sistema de arquivos do host:

    sudo docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/tools/summarize.rb ./summarize.rb
    
  3. Agora edite o arquivo, substitua o prompt do sistema em inglês pelo idioma desejado:

    Resumo
           system_prompt = <<~TEXT
           You are a summarization bot.
           You effectively summarise any text.
           You condense it into a shorter version.
           You understand and generate Discourse forum markdown.
           Try generating links as well the format is #{topic.url}/POST_NUMBER. eg: [ref](#{topic.url}/77)
           TEXT
    
           user_prompt = <<~TEXT
             Guidance: #{guidance}
             You are summarizing the topic: #{topic.title}
             Summarize the following in 400 words:
    
             #{text}
           TEXT
    

    Resultado, por exemplo:

           system_prompt = <<~TEXT
           Вы — бот, выполняющий суммаризацию текста.
           Вы умеете эффективно сокращать текст до ключевых мыслей.
           Вы понимаете и умеете генерировать разметку Markdown в Discourse.
           При необходимости добавляйте ссылки в формате: #{topic.url}/POST_NUMBER, например: [ссылка](#{topic.url}/77)
           TEXT
    
           user_prompt = <<~TEXT
             Руководство: #{guidance}
             Вы суммаризуете топик: #{topic.title}
             Пожалуйста, предоставь ответ на русском языке.
             В ответе используй 400 слов:
    
             #{text}
           TEXT
    
  4. Em seguida, faça o mesmo para o segundo arquivo:

    sudo docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/summarizer.rb ./summarizer.rb
    

    Edite:

    Nota: você pode substituir o idioma do texto original:

    - Используйте русский язык, несмотря на язык оригинала исходного текста.
    
    Resumo
         <<~PROMPT.strip
           You are an advanced summarization bot that generates concise, coherent summaries of provided text.
           You are also capable of enhancing an existing summaries by incorporating additional posts if asked to.
    
           - Only include the summary, without any additional commentary.
           - You understand and generate Discourse forum Markdown; including links, _italics_, **bold**.
           - Maintain the original language of the text being summarized.
           - Aim for summaries to be 400 words or less.
           - Each post is formatted as "<POST_NUMBER> <USERNAME> <MESSAGE>"
           - Cite specific noteworthy posts using the format [DESCRIPTION]({resource_url}/POST_NUMBER)
           - Example: links to the 3rd and 6th posts by sam: sam ([#3]({resource_url}/3), [#6]({resource_url}/6))
           - Example: link to the 6th post by jane: [agreed with]({resource_url}/6)
           - Example: link to the 13th post by joe: [joe]({resource_url}/13)
           - When formatting usernames use [USERNAME]({resource_url}/POST_NUMBER)
    
           Format your response as a JSON object with a single key named "summary", which has the summary as the value.
           Your output should be in the following format:
             <output>
               {"summary": "xx"}
             </output>
    
           Where "xx" is replaced by the summary.
         PROMPT
       end
    
    ...
           [
             "Here are the posts inside <input></input> XML tags:\n\n<input>1) user1 said: I love Mondays 2) user2 said: I hate Mondays</input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language.",
             {
               summary:
                 "Two users are sharing their feelings toward Mondays. [user1]({resource_url}/1) hates them, while [user2]({resource_url}/2) loves them.",
             }.to_json,
           ],
    

    Resultado:

            <<~PROMPT.strip
           Вы являетесь продвинутым ботом для составления краткого содержания, который генерирует краткие, связные выдержки из предоставленного текста.
           Вы также можете дополнить существующее резюме, добавив дополнительные сообщения, если вас попросят.
    
           - Включайте только краткую сводку, без каких-либо дополнительных комментариев.
           - Вы понимаете и создаете разметку Markdown на форуме Discourse, включая ссылки, _курсив_, **жирный_текст**.
           - Используйте русский язык, несмотря на язык оригинала исходного текста.
           - Старайтесь, чтобы объем резюме не превышал 400 слов.
           - Каждая запись оформляется как "<POST_NUMBER> <USERNAME> <MESSAGE>"
           - Цитируйте конкретные заслуживающие внимания публикации, используя формат [DESCRIPTION]({resource_url}/POST_NUMBER)
           - Пример: ссылки на 3-й и 6-й посты пользователя sam: sam ([#3]({resource_url}/3), [#6]({resource_url}/6))
           - Пример: ссылка на 6-е сообщение пользователя jane: [согласовано с]({resource_url}/6)
           - Пример: ссылка на 13-е сообщение Джо: [Джо]({resource_url}/13)
           - При форматировании имен пользователей используйте [USERNAME]({resource_url}/POST_NUMBER)
    
           Отформатируйте свой ответ в виде объекта JSON с помощью единственного ключа с именем "summary", который имеет значение "summary".
           Ваши выходные данные должны быть в следующем формате:
             <output>
               {"summary": "xx"}
             </output>
    
           Где "xx" заменяется на текст краткой сводки.
         PROMPT
       end
    
       def response_format
         [{ "key" => "summary", "type" => "string" }]
       end
    
       def examples
         [
           [
             "Вот записи внутри XML-тегов <input></input>:\n\n<input>1) user1 сказал: Я люблю понедельники 2) user2 сказал: А я ненавижу понедельники</input>\n\nСформулируйте краткое, связное изложение текста выше, сохранив язык оригинала.",
             {
               summary:
                 "Два пользователя делятся своими чувствами к понедельникам. [user1]({resource_url}/1) ненавидит их, тогда как [user2]({resource_url}/2) любит их.",
             }.to_json,
           ],
    
  5. Copie os arquivos modificados para o contêiner:

    sudo docker cp summarize.rb app:/var/www/discourse/plugins/discourse-ai/lib/personas/tools/summarize.rb
    sudo docker cp summarizer.rb app:/var/www/discourse/plugins/discourse-ai/lib/personas/summarizer.rb
    
  6. Em seguida, confirme e reinicie o contêiner:

    sudo docker commit app
    sudo /var/discourse/launcher restart app
    
  7. Verifique o resultado (para novos tópicos):

Não há necessidade de fazer tudo isso, você pode alterar a Persona que faz a sumarização nas configurações de administrador agora.

Crie uma nova Persona seguindo as configurações da existente, altere o prompt do sistema como desejar e defina o recurso de sumarização para usá-la em /admin/plugins/discourse-ai/ai-features/1/edit.

2 curtidas

Bem… As últimas palavras sobre suporte a idiomas foram encontradas neste tópico. Obrigado pela resposta.

A primeira tentativa de criar um bot de sumarização adequado como um clone de um bot existente falhou. Ele ainda produz inglês. Provavelmente estou fazendo algo errado.

Não tenho certeza de quão bem você se sairá com este modelo, ele não é tão poderoso

1 curtida

Qual é a solução alternativa ou abordagem de todos para a sumarização de IA não em inglês?

Por exemplo, para resumos de bate-papo enquanto a Localidade está definida como Alemão, ainda recebo resumos em idioma INGLÊS, também com links de markdown de texto claro para mensagens de bate-papo individuais não formatados corretamente como links.

Testado com Gemini 2.5 Lite

1 curtida

Olá, eu ainda uso a solução alternativa descrita acima. Tentei truques com Personas personalizadas, mas não funcionou. Provavelmente estou fazendo algo errado, mas para mim é menos doloroso.

Como um breve resumo, você preparará os modelos baixados do GitHub, modificará para suas necessidades e aplicará cada vez após a reconstrução. Não se esqueça de verificar novas versões desses arquivos a cada 2-3 meses.

Crie um script executável (no diretório $HOME) do_it_after_rebuild.sh

#/bin/bash
#
# https://github.com/discourse/discourse/tree/main/plugins/discourse-ai/lib/personas
docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/tools/summarize.rb orig_summarize.rb
docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/summarizer.rb orig_summarizer.rb
docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/short_summarizer.rb orig_short_summarizer.rb
docker cp app:/var/www/discourse/plugins/discourse-ai/lib/personas/discover.rb orig_discover.rb

rm GeoLite2*
wget https://raw.githubusercontent.com/8bitsaver/maxmind-geoip/release/GeoLite2-City.mmdb
wget https://raw.githubusercontent.com/8bitsaver/maxmind-geoip/release/GeoLite2-ASN.mmdb

docker cp GeoLite2-City.mmdb    app:/var/www/discourse/vendor/data/
docker cp GeoLite2-ASN.mmdb     app:/var/www/discourse/vendor/data/
docker cp summarize.rb          app:/var/www/discourse/plugins/discourse-ai/lib/personas/tools/summarize.rb
docker cp summarizer.rb         app:/var/www/discourse/plugins/discourse-ai/lib/personas/summarizer.rb
docker cp short_summarizer.rb   app:/var/www/discourse/plugins/discourse-ai/lib/personas/short_summarizer.rb
docker cp discover.rb           app:/var/www/discourse/plugins/discourse-ai/lib/personas/discover.rb
docker commit app
sudo /var/discourse/launcher restart app

E execute após a reconstrução:

./do_it_after_rebuild.sh
Arquivos aqui

Faça estas alterações nos arquivos que você precisa baixar periodicamente de aqui (eu mostro apenas diffs - você tem que adicionar essas linhas nos arquivos manualmente):

diff discover.rb orig_discover.rb
35d34
<         * Use always German language.
80d78
<
└─# diff short_summarizer.rb orig_short_summarizer.rb
12c12,13
< Du bist ein fortgeschrittener Bot, um den Text zusammenzufassen. Sie analysieren den bereitgestellten Text und erzeugen eine kurze Zusammenfassung aus einem einzigen Satz, in dem das Hauptthema und die aktuellen Ereignisse dem Gesprächspartner ohne vorläufigen Kontext verständlich sind.
---
> You are an advanced summarization bot. Analyze a given conversation and produce a concise,
> single-sentence summary that conveys the main topic and current developments to someone with no prior context.
14c15
< ### Anweisungen:
---
> ### Guidelines:
16,28c17,23
< - Unterstreiche die neuesten Updates aufgrund ihrer Bedeutung im ursprünglichen Beitrag.
< - Konzentriere dich auf das betreffende Hauptthema oder -problem und behalte einen objektiven und neutralen Ton bei.
< - Schließen Sie fremde Details oder subjektive Meinungen aus.
< - Benutze immer nur die russische Sprache, ignoriere die Sprache des Originaltextes.
<
---
> - Underline the latest updates due to their importance in the original post.
> - Focus on the main topic or issue at hand and maintain an objective and neutral tone.
> - Exclude extraneous details or subjective opinions.
> - Always use only the Russian language, ignore the language of the original text.
>
└─# diff summarizer.rb orig_summarizer.rb
12,13c12,13
< Sie sind ein fortgeschrittener Bot, um kurze Inhalte zu erstellen, die kurze, zusammenhängende Auszüge aus dem bereitgestellten Text erzeugen.
< Sie können einen vorhandenen Lebenslauf auch ergänzen, indem Sie zusätzliche Beiträge hinzufügen, wenn Sie dazu aufgefordert werden.
---
> You are an advanced summarization bot that generates concise, coherent summaries of provided text.
> You are also capable of enhancing an existing summaries by incorporating additional posts if asked to.
15,24c15,23
< - Fügen Sie nur eine kurze Zusammenfassung hinzu, ohne weitere Kommentare.
< - Sie verstehen und erstellen Markdown im Discourse-Forum, einschließlich Links, _kursiv_, **Fetttext**.
< - Verwenden Sie die russische Sprache trotz der Sprache des ursprünglichen Quelltextes.
< - Versuchen Sie, den Lebenslauf auf 400 Wörter zu beschränken.
< - Jeder Eintrag wird als "<POST_NUMBER>) <USERNAME> <MESSAGE>" ausgegeben
< - Zitieren Sie bestimmte bemerkenswerte Publikationen mit dem Format [BESCHREIBUNG]({resource_url}/POST_NUMBER)
< - Beispiel: Links zu den 3. und 6. Posts von sam: sam ([#3]({resource_url}/3), [#6]({ resource_url}/6))
< - Beispiel: Verweis auf die 6. Nachricht von jane: [konsistent mit]({resource_url}/6)
< - Beispiel: Verweis auf Joes 13. Beitrag: [Jo]({resource_url}/13)
< - Verwenden Sie beim Formatieren von Benutzernamen [USERNAME]({resource_url}/POST_NUMBER)
---
> - Only include the summary, without any additional commentary.
> - You understand and generate Discourse forum Markdown; including links, _italics_, **bold**.
> - Maintain the original language of the text being summarized.
> - Aim for summaries to be 400 words or less.
> - Every post is formatted as "<POST_NUMBER>) <USERNAME> <MESSAGE>"
> - Cite specific notable posts in the format [DESCRIPTION]({resource_url}/POST_NUMBER)
> - Example: Links to the 3rd and 6th posts by sam: sam ([#3]({resource_url}/3), [#6]({ resource_url}/6))
> - Example: Reference to jane's 6th message: [consistent with]({resource_url}/6)
> - Example: Reference to joe's 13th post: [joe]({resource_url}/13)
> - Use [USERNAME]({resource_url}/POST_NUMBER) when formatting usernames
Nr.26,30c25,28
< Отформатируйте свой ответ в виде объекта JSON с помощью единственного ключа с именем "Zusammenfassung", который имеет значение "Zusammenfassung".
< Ваши выходные данные должны быть в следующем формате:
< 
< {"zusammenfassung": "xx"}
< 
---
> Format your response as a JSON object with a single key named "summary" that has the summary as its value.
> Your output should be in the following format:
> 
> {"summary": "xx"}
32c30,31
< Wobei "xx" durch den Text der Zusammenfassung ersetzt wird.
---
> Where "xx" is replaced by the summary.
> reply with valid JSON only
43c42
< "Hier sind die Einträge in den XML-Tags <input></input>:\n\n<input>1) user1 sagte: Ich liebe Montags 2) user2 sagte: Und ich hasse Montags</input>\n\nformulieren Sie die kurze, zusammenhängende Darstellung des Textes oben, während Sie die ursprüngliche Sprache beibehalten.",
---
> "Here are the posts inside <input></input> XML tags:\n\n<input>1) user1 said: I love Mondays 2) user2 said: I hate Mondays</input>\n\nGenerate a concise, coherent summary of the text above maintaining the original language.",
46c45
< "Zwei Benutzer teilen ihre Gefühle für Montag. [user1]({resource_url}/1) hasst sie, während [user2]({resource_url}/2) sie liebt.",
---
> "Two users are sharing their feelings toward Mondays. [user1]({resource_url}/1) hates them, while [user2]({resource_url}/2) loves them.",
└─# diff summarize.rb orig_summarize.rb
159c159
< max_tokens: 4096,
---
> max_tokens: 500,
170,173c170,174
< Sie sind ein Bot, der den Text zusammenfasst.
< Sie sind in der Lage, Text effektiv auf wichtige Gedanken zu reduzieren.
< Sie verstehen und können Markdown-Markdown in Discourse generieren.
< Fügen Sie bei Bedarf Links im Format #{topic.url}/POST_NUMBER hinzu, zum Beispiel: [link](#{topic.url}/77)
---
> You are a summarization bot.
> You effectively summarise any text.
> You condense it into a shorter version.
> You understand and generate Discourse forum markdown.
> Try generating links as well the format is #{topic.url}/POST_NUMBER. eg: [ref](#{topic.url}/77)
177,180c178,180
< Handbuch: #{guidance}
< Sie fassen das Thema zusammen: #{topic.title}
< Bitte gib eine Antwort auf Russisch an.
< Benutze 400 Wörter in deiner Antwort:
---
>