Translate values

OpenAI GPT-3x & more, Google Gemini Pro, trained on a massive dataset of text from the internet, is capable of generating text in a variety of languages, including English, Spanish, French, Chinese, Russian, and many more. Nevertheless, it is important to bear in mind that the model’s performance will vary depending on the language and the complexity of the text to be generated.

List of locales available with OpenAI.

Number	Language	Country	Local Translation
1	Albanian	Albania	Shqip
2	Arabic	Arab World	العربية
3	Armenian	Armenia	Հայերեն
4	Awadhi	India	अवधी
5	Azerbaijani	Azerbaijan	Azərbaycanca
6	Bashkir	Russia	Башҡорт
7	Basque	Spain	Euskara
8	Belarusian	Belarus	Беларуская
9	Bengali	Bangladesh	বাংলা
10	Bhojpuri	India	भोजपुरी
11	Bosnian	Bosnia and Herzegovina	Bosanski
12	Brazilian Portuguese	Brazil	português brasileiro
13	Bulgarian	Bulgaria	български
14	Cantonese (Yue)	China	粵語
15	Catalan	Spain	Català
16	Chhattisgarhi	India	छत्तीसगढ़ी
18	Chinese	China	中文
19	Croatian	Croatia	Hrvatski
20	Czech	Czech Republic	Čeština
21	Danish	Denmark	Dansk
22	Dogri	India	डोगरी
23	Dutch	Netherlands	Nederlands
24	English	United Kingdom	English
25	Estonian	Estonia	Eesti
26	Faroese	Faroe Islands	Føroyskt
27	Finnish	Finland	Suomi
28	French	France	Français
29	Galician	Spain	Galego
30	Georgian	Georgia	ქართული
31	German	Germany	Deutsch
32	Greek	Greece	Ελληνικά
33	Gujarati	India	ગુજરાતી
34	Haryanvi	India	हरियाणवी
35	Hindi	India	हिंदी
36	Hungarian	Hungary	Magyar
37	Indonesian	Indonesia	Bahasa Indonesia
37	Irish	Ireland	Gaeilge
38	Italian	Italy	Italiano
39	Japanese	Japan	日本語
40	Javanese	Indonesia	Basa Jawa
41	Kannada	India	ಕನ್ನಡ
42	Kashmiri	India	कश्मीरी
43	Kazakh	Kazakhstan	Қазақша
44	Konkani	India	कोंकणी
45	Korean	South Korea	한국어
46	Kyrgyz	Kyrgyzstan	Кыргызча
47	Latvian	Latvia	Latviešu
48	Lithuanian	Lithuania	Lietuvių
49	Macedonian	North Macedonia	Македонски
50	Maithili	India	मैथिली
51	Malay	Malaysia	Bahasa Melayu
52	Maltese	Malta	Malti
53	Mandarin	China	普通话
54	Mandarin Chinese	China	中文
55	Marathi	India	मराठी
56	Marwari	India	मारवाड़ी
57	Min Nan	China	閩南語
58	Moldovan	Moldova	Moldovenească
59	Mongolian	Mongolia	Монгол
60	Montenegrin	Montenegro	Crnogorski
61	Nepali	Nepal	नेपाली
62	Norwegian	Norway	Norsk
63	Oriya	India	ଓଡ଼ିଆ
64	Pashto	Afghanistan	پښتو
65	Persian (Farsi)	Iran	فارسی
66	Polish	Poland	Polski
67	Portuguese	Portugal	Português
68	Punjabi	India	ਪੰਜਾਬੀ
69	Rajasthani	India	राजस्थानी
70	Romanian	Romania	Română
71	Russian	Russia	Русский
72	Sanskrit	India	संस्कृतम्
73	Santali	India	संताली
74	Serbian	Serbia	Српски
75	Sindhi	Pakistan	سنڌي
76	Sinhala	Sri Lanka	සිංහල
77	Slovak	Slovakia	Slovenčina
78	Slovene	Slovenia	Slovenščina
79	Slovenian	Slovenia	Slovenščina
90	Ukrainian	Ukraine	Українська
91	Urdu	Pakistan	اردو
92	Uzbek	Uzbekistan	Ўзбек
93	Vietnamese	Vietnam	Việt Nam
94	Welsh	Wales	Cymraeg
95	Wu	China	吴语

Step 0 : Click on the “Translate values” pattern

Step 1 : Select the Akeneo instance to connect to

With your subscription, you can connect 1 production instance and as many staging instances as you need. Test your prompts before feeding your production !

Step 2 : Choose the right AI model you want to use

We regularly update our range of models, introducing new ones as well as enhanced versions.

Each model is unique and can be suited to different contexts. For instance, older models like GPT-3.5 Turbo, which are much more cost-effective, are particularly suitable for generating internal or low-visibility content (e.g., meta descriptions). In contrast, the latest models are recommended for creating high-quality content or handling a larger volume of data.

It’s important to note that models from GPT-4 Turbo and Google Gemini Pro onwards are clearly better in translation.

The choice of AI model to use is made directly by clicking on the model. It can be adapted for each pattern, making BeeApp highly flexible in terms of cost optimization and data quality.

Step 3 : Select the products to be enriched

This step is crucial because it allows you to choose the products you want to work on using static or dynamic filters.

• Static Filters: You can select one or more specific products (product model and variant) by using their identifier.
• Dynamic Filters: You can select products using various filters available in Akeneo, such as families, categories, and any text, number, date, or boolean attribute configured in your instance. If these attributes are localized or scoped, you can precise the locale & channels to use.

This feature is powerful because it lets you schedule regular executions. Therefore, any new product meeting these criteria will be included in the process defined in Step 4.

To use the filters, enter the attribute codes. An autocomplete feature is available: simply type the first few letters of the family, category, or attribute code to see the available options.

By combining different attribute values with families and categories, you can identify parts of your catalog and contextualize your new content more efficiently.

Example : I want to translate all my products of the family “Led TVs” (code : led_tvs) whose description (code of the attribute : description) is empty (for the locale fr_FR and the ecommerce channel)

After entering the code of the attribute, if the attribute does not exist in your Akeneo instance, an error message will be displayed under the input field.

💡The more precise you are, the better the content generated will be. That’s why we advise you to make small selections of products and to adapt specific content in step 3.

💡To avoid overwriting an existing value, remember to add a filter for the value to be enriched that is not empty.

Step 4 : Configure the content to translate

Characteristic to be translated

Enter the attribute code to translate.

💡 Only attributes of type “text” and “textarea” can be translated through this pattern.

Source language

Select the initial locale of the content to be translated. The list displayed corresponds to the locales configured in Akeneo.

Target languages

Select the locales in which to translate the content. The list displayed corresponds to the locales configured in Akeneo. It is possible to select several locales if you want simultaneous translations.

Lexicon

In order to improve the quality of the translation (especially in the case of certain terms that may have several meanings), we recommend that you add the lexical field of the product or selection of products to be translated.

Example : Personal Protective Equipment, haberdashery, food, electronic, wheel and gear…

Custom Instructions

Custom instructions can be used to improve translation quality through additional instructions. For example, when translating from English into French, it may be appropriate to add a custom instruction indicating whether to translate “you” as “tutoie” or “vouvoie”.

Glossary

In some cases, it may also be necessary to force the translation of certain terms into a specific locale.

It is now possible to force these translations by creating a glossary (To find out how to create a glossary, click here). Once a glossary has been created, you can select it directly from the drop-down list.

Loading a glossary increases the cost of input tokens. To limit this cost, don’t hesitate to create glossaries by product category, by locale… there’s no limit to the number of glossaries you can create with Bee.

Step 4 : Save and run

Before finalizing and executing your prompt, Bee specifies the number of products corresponding to your selection of products by separating the number of products and the number of product models.

Save pattern

You can save the pattern you have just configured in order to be able to program, in a second time, a recurrence of execution or a manual launch. All your saved patterns are accessible from the “Patterns” tab in the left menu.

This newly created prompt can be accessed from the “Patterns” link located in the left menu.