Skip to content
Nappai Documentation

Text Extractor

This component is a lightweight, easy-to-use tool in the Nappai dashboard designed to pull text and data from your files, reports, or data sources. Instead of requiring you to build complex extraction rules, the Text Extractor acts as a smart bridge that prepares your raw data for the rest of your automation workflow. You can drop it into your dashboard and let it handle the heavy lifting of text preparation, ensuring your information flows smoothly between different automation stages.

How it Works

This component works behind the scenes as a streamlined connector. When you add it to your workflow, Nappai automatically links it to the system’s standard text processing engine. You do not need to write code or configure complex rules. Simply connect your data source to this node, and it will automatically scan the input, identify readable text, and prepare the extracted information for the next step in your graph.

The actual extraction logic is managed by Nappai’s core system, so you only interact with a clean, user-friendly interface. As data passes through, the component packages it into a format that other automation tools can easily understand, ensuring that downstream steps receive consistent and usable information.

Inputs

This component automatically receives data from previous steps in your workflow. You do not need to manually configure input fields, as the Nappai dashboard handles the connection based on the type of data flowing into the node. Simply drag your workflow from a previous step to connect them, and the extractor will know exactly how to process the incoming text. If your workflow requires additional configuration, the dashboard will automatically prompt you only when necessary.

Outputs

Once the Text Extractor processes your data, it outputs clean, ready-to-use text that can be passed to other components in your automation graph. This output typically includes the extracted text content along with basic metadata (such as source type or extraction status), allowing downstream tools to interpret and act on the data without errors. The result is packaged as a structured data object that can be mapped directly to AI analysis, database storage, or reporting tools.

Output Data Example (JSON)json

{ “extracted_text”: “This is a sample document containing automated workflows and key data points.”, “status”: “success”, “source_type”: “document”, “metadata”: { “language”: “en”, “char_count”: 87, “extracted_at”: “2024-01-15T10:30:00Z” } }

Connectivity

In a typical Nappai workflow, the Text Extractor is placed early in the automation chain, right after data sources or file upload steps. Its output ports are designed to connect seamlessly with:

  • Text Analysis & AI Nodes: To send clean text for summarization, translation, or sentiment analysis.
  • Data Storage & CRM Components: To save extracted information into databases, spreadsheets, or customer records.
  • Automation Triggers: To kick off further actions once the data is verified and ready. This logical flow ensures that messy or raw data is standardized before it reaches more complex processing tools, preventing errors and improving overall workflow reliability.

Usage Example

Imagine you receive a batch of PDF reports from clients and need to summarize the key findings. You can:

  1. Connect a File Uploader or Data Fetcher component to the Text Extractor.
  2. The extractor automatically pulls out the readable text from each PDF, ignoring formatting, images, and unreadable characters.
  3. Pass the extracted text to an AI Assistant node for summarization or keyword extraction.
  4. Route the final summary to a Database or Email Sender component for reporting. This setup eliminates manual copy-pasting and ensures consistent data handling across every report.

Tips and Best Practices

  • Place the Text Extractor as early as possible in your workflow to prevent downstream errors caused by unclean or raw data.
  • Ensure your data sources support standard text formats for the best extraction results.
  • If working with large files, consider adding a pagination or chunking step before the extractor to avoid performance bottlenecks.
  • Use the output metadata fields (like source_type or status) to create conditional branching in your workflow for better error handling.

Security Considerations

  • The component processes data within Nappai’s secure environment and does not expose raw files to external services unless explicitly connected.
  • Avoid feeding sensitive or personally identifiable information (PII) directly into extraction nodes without first applying data masking or anonymization steps.
  • Regularly audit your workflow connections to ensure that extracted data is only routed to authorized and trusted downstream components.