Split Text
Split Text is a handy tool that takes a long piece of text and breaks it into smaller, more manageable pieces. This makes it easier to feed the text into other parts of your automation workflow, like summarizers, translators, or AI models that prefer shorter inputs.
How it Works
The component works entirely inside your dashboard—no external calls are made. It takes the text you provide, then:
- Chooses a separator (by default a newline, but you can pick any character or string).
- Cuts the text into chunks that are no longer than the Chunk Size you set.
- Adds a little overlap between consecutive chunks if you want the context to carry over.
- Returns each chunk as a separate Data item that can be used by other components.
Because everything happens locally, the process is fast and keeps your data private.
Inputs
- Data Inputs: The text (or collection of texts) you want to split.
- Chunk Overlap: How many characters should be repeated at the start of each new chunk. This helps keep context when the chunks are processed separately.
- Chunk Size: The maximum number of characters in each chunk.
- Separator: The character or string that tells the splitter where a natural break can happen (e.g., a newline, a period, or a custom delimiter).
Outputs
- Chunks: A list of Data items, each containing one of the split text pieces. These can be fed into other components like “Summarize Text” or “Translate Text”.
Usage Example
- Add the Split Text component to your workflow.
- Connect a “Read File” or “Get Text” component to the Data Inputs field.
- Set Chunk Size to 1000 and Chunk Overlap to 200 (or whatever fits your needs).
- Leave the Separator as the default newline or change it to a period if you prefer sentence‑level splits.
- Connect the Chunks output to a “Summarize Text” component.
- Run the workflow—each chunk will be summarized separately, and you’ll get a concise overview of the entire document.
Related Components
- Merge Text – Combine multiple text pieces back into one.
- Extract Text – Pull specific sections from a document before splitting.
- Summarize Text – Create short summaries of each chunk.
- Translate Text – Convert each chunk into another language.
Tips and Best Practices
- Choose a sensible Chunk Size: Too small and you lose context; too large and downstream models may choke.
- Use Chunk Overlap when the next chunk depends on the previous one—this keeps continuity.
- Pick a clear Separator: If your text is paragraph‑based, a newline works well; for sentence‑based splitting, use a period.
- Test with a sample: Run the splitter on a small portion first to see how the chunks look.
- Combine with Merge Text if you need to reassemble the processed chunks later.
Security Considerations
The Split Text component processes data locally within the Nappai dashboard. No external APIs are called, so your text stays on your own infrastructure. Just be mindful of any sensitive information you feed into the component—handle it according to your organization’s data‑handling policies.