WorqHat
AI Nodes

Text Extraction

Category
AI
Node Type
Data Processing

Overview

The Text Extraction node uses AI to extract text and metadata from different content sources such as PDFs, web pages, images, or audio files. It converts raw files or URLs into structured, readable text that can be used by other nodes in your workflow.

Description

Extract text and metadata from documents, websites, images, and audio.

This node is designed to automatically pull text and metadata from a variety of input formats. Depending on the selected extraction type, it can process different kinds of media.

PDF Extraction

Read and extract text from PDF documents.

Web Extraction

Capture and process the textual content and metadata of a webpage.

Image Extraction

Identify and read text from images (OCR-based).

Audio Extraction

Convert speech-to-text from audio files.

It helps automate content analysis, data gathering, and transcription workflows with minimal setup.

Input Parameters

The Text Extraction node accepts flat key-value inputs that determine the source and method of text extraction.

extractionTypestringRequired
Defines the type of extraction to perform.
Example
"pdf-extraction", "web-extraction", "image-extraction", "audio-extraction"
webUrlstringOptional
The URL of the web page to extract content from. Required only for 'web-extraction'.
Example
"https://example.com/article"
attachmentsstringOptional
Comma-separated list of file IDs or variable references to uploaded files. Required for 'pdf-extraction', 'image-extraction', and 'audio-extraction'.
Example
"file1.pdf,file2.pdf" or "{{nodeId.output.file1}}"
Instructions

Provide flat key-value pairs for all input parameters.

  • For multiple files, separate entries with commas.
  • You can dynamically reference data from previous nodes using: {{nodeId.input.<key>}}

Output Parameters

After execution, the Text Extraction node returns the extracted text along with processing information and detailed metadata. The available outputs depend on the extractionType.

Common Outputs (All Types)

contentstringOptional
The main text extracted from the provided source.
Example
"Extracted text content..."
processingCountnumberOptional
Number of files, pages, or segments processed.
Example
1
processingTimestringOptional
Total time taken for extraction (ISO timestamp).
Example
"2025-10-27T12:05:43Z"
processingIdstringOptional
Unique identifier for the request.
Example
"proc_67892"

PDF Extraction Outputs

markdownstringOptional
Markdown-formatted version of the extracted text.
Example
"**Title**\n\nBody text..."
metadataobjectOptional
Metadata about the PDF document.
Example
{ "title": "Report.pdf", "pages": 5 }

Web Extraction Outputs

markdownstringOptional
Markdown-formatted version of the webpage content.
Example
"# Page Title\n\nArticle content..."
linksOnPage[]arrayOptional
List of all hyperlinks found on the page.
Example
["https://example.com/link1", "https://example.com/link2"]
metadataobjectOptional
Webpage metadata including title, description, keywords, and Open Graph tags.
Example
{ "title": "Page Title", "description": "...", "ogImage": "..." }

Image Extraction Outputs

contentstringOptional
Text extracted from the image via OCR.
Example
"Invoice #12345..."

Audio Extraction Outputs

speaker_labels[]arrayOptional
List of speaker segments with their spoken text.
Example
[{ "speaker": "Speaker 1", "text": "Hello" }]
timestamps[]arrayOptional
Word-level timestamps for the transcription.
Example
[{ "word": "Hello", "startTime": 0.5, "endTime": 1.0 }]
Accessing Data

Access output values using variables like:

{{nodeId.output.content}}                 → Extracted text
{{nodeId.output.metadata.title}}          → Page or document title
{{nodeId.output.linksOnPage[0]}}          → First link on the page
{{nodeId.output.speaker_labels[0].text}}  → First speaker’s text segment

Output Type

Output Type: text

The output type must always be exactly:

"text"

This ensures the node consistently provides extracted text output, regardless of the extraction source (PDF, web, image, or audio).

Example Usage

Example 1: Extract Text from a PDF

{  "extractionType": "pdf-extraction",  "attachments": "file123.pdf"}
{  "content": "This is the text extracted from the PDF document.",  "processingId": "proc_67892",  "processingTime": "2025-10-27T12:05:43Z",  "processingCount": 1}

Example 2: Extract Text from Image

{  "extractionType": "image-extraction",  "attachments": "image123.png"}
{  "content": "Here is the article content extracted from the page...",  "processingTime": "2025-10-27T12:06:11Z",  "processingId": "output-1761738927697",  "processingCount": 41}

Example 3: Extract Text from Audio

{  "extractionType": "audio-extraction",  "attachments": "nature_audio.mp3"}
{  "content": "The evening sky was painted with shades of orange and violet...",  "processingTime": "2025-10-27T12:05:43Z",  "processingId": "dc9509af-3783-48bd-8819-85126a8e66a8",  "processingCount": 188}

How to Use in a No-Code Workflow

1

Add the Text Extraction Node

Drag and drop the node into your workflow.

2

Select Extraction Type

Choose the appropriate extraction type:

  • "pdf-extraction" for PDF files
  • "web-extraction" for web pages
  • "image-extraction" for scanned images or screenshots
  • "audio-extraction" for speech-to-text conversion
3

Provide Input

  • For PDFs, images, or audio: add file references under attachments.
  • For webpages: enter the target URL in webUrl.
4

Run the Node

The node will extract text, metadata, or transcription automatically.

5

Access Results

Use variable syntax to retrieve outputs such as:

{{textExtraction.output.content}}
{{textExtraction.output.metadata.title}}
6

Connect to Next Nodes

You can pass the extracted text to other nodes like Text Generation, AI Analysis, or Summarization for further automation.

Best Practices

  • Ensure the correct extraction type is selected before execution.
  • When extracting from multiple files, separate file IDs with commas.
  • For web extractions, make sure the URL is publicly accessible.
  • Use OCR-friendly images (clear text visibility) for best results.
  • For large audio files, split them into smaller segments to improve performance.
  • Always review extracted content for accuracy before using it in production workflows.

Common Errors

Missing extractionTypeErrorOptional
No extraction type was provided. Always specify one of 'pdf-extraction', 'web-extraction', 'image-extraction', or 'audio-extraction'.
Missing webUrlErrorOptional
The webUrl field is required for 'web-extraction'. Add a valid, publicly accessible URL.
Missing attachmentsErrorOptional
No file references provided for file-based extraction. Add valid file IDs or variable references in the attachments field.
Unsupported file formatErrorOptional
The file type is not supported for extraction. Use PDF, image, or audio files in standard formats.
Empty outputErrorOptional
The AI was unable to extract content from the provided source. Recheck file quality, accessibility, or try a different extraction type.

Example Workflow Integration

Use Case 1: Summarize a PDF Report

Automatically extract text from an uploaded PDF and generate a summary.

  1. File Upload Node – Receives the PDF file.
  2. Text Extraction Node – Extracts text using pdf-extraction.
  3. Text Generation Node – Summarizes the extracted content.
  4. Email Node – Sends the summary to the user.

Workflow Data Flow:

{{fileUpload.output.fileId}}        →  {{textExtraction.input.attachments}}
{{textExtraction.output.content}}   →  {{textGeneration.input.prompt}}

Use Case 2: Web Scraping & Analysis

Extract content from a competitor's blog post and analyze the sentiment.

  1. REST API Trigger – Receives the blog URL.
  2. Text Extraction Node – Extracts text and metadata using web-extraction.
  3. Text Generation Node – Analyzes the sentiment of the article.
  4. Database Node – Stores the analysis results.

Workflow Data Flow:

{{trigger.input.url}}               →  {{textExtraction.input.webUrl}}
{{textExtraction.output.content}}   →  {{textGeneration.input.prompt}}

Use Case 3: Receipt Processing (Image)

Extract data from a photo of a receipt for expense tracking.

  1. WhatsApp Trigger – User sends a photo of a receipt.
  2. Text Extraction Node – Extracts text using image-extraction.
  3. Text Generation Node – Extracts structured JSON (date, amount, vendor) from the text.
  4. Google Sheets Node – Adds a new row with the expense details.

Workflow Data Flow:

{{whatsapp.output.mediaId}}         →  {{textExtraction.input.attachments}}
{{textExtraction.output.content}}   →  {{textGeneration.input.prompt}}

Use Case 4: Meeting Transcription (Audio)

Transcribe a meeting recording and email the minutes.

  1. File Upload Node – User uploads an MP3 recording.
  2. Text Extraction Node – Transcribes audio using audio-extraction.
  3. Text Generation Node – Generates meeting minutes from the transcription.
  4. Email Node – Sends the minutes to all attendees.

Workflow Data Flow:

{{fileUpload.output.fileId}}        →  {{textExtraction.input.attachments}}
{{textExtraction.output.content}}   →  {{textGeneration.input.prompt}}