Text Translation

Step 1. Set Input Dataset

Consider a dataset containing product descriptions in English that need to be translated into Spanish. Here is a sample dataset before translation:

{{line}}

Step 2. Define the AI Prompt

Prompt Example

Translate the product description in @Description_English from English to Spanish. Keep the translation concise and relevant to the original context.

Why This Prompt Is Good

• Clearly states the task (translation) and the language pair (English to Spanish).
• Emphasizes keeping the translation concise, avoiding overly verbose translations.
• Ensures the translation remains true to the original meaning.

{{line}}

Step 3. Configure the Flow Designer

1. Add the input dataset to the flow designer.
2. Select the AI Column node from the tools panel and enter the prompt.
3. Start with a row-by-row execution to fine-tune your prompt.
4. Correct your prompt, regenerate any single row, or remove all previous results.
5. Once you satisfied with the prompt, apply the AI Column Node to all rows (it will be applied only for empty cells).
6. For very large datasets that are bigger than 10,000 rows, run the flow for runtime processing over the whole dataset. Be aware that it can be costly for a large amount of data.

{{line}}

Step 4. Get Final Result

Here is the dataset after using the AI Column Node to translate the descriptions: