Convert PDF URL to Text

The "Convert PDF URL to Text" step allows you to extract the textual content from a PDF document available at a specified URL. This powerful tool enables you to analyze, process, and work with text content from PDFs without manual copying or extraction.

How to Configure the Convert PDF URL to Text Step

Configuring the step requires setting the parameters shown below:

[IMAGE: Screenshot of the Convert PDF URL to Text step configuration panel]

PDF URL

Enter the full URL of the PDF document you want to convert to text. This should be a direct link to a PDF file accessible via the internet.

You can use Liquid syntax to dynamically reference a PDF URL from a previous step:

{{ step_1.output.pdf_url }}

Important: The URL must point directly to a PDF file that is publicly accessible. Password-protected PDFs cannot be processed.

Page Range (Optional)

Specify which pages of the PDF document you want to extract:

• All Pages (default): Extract text from the entire document

• Specific Pages: Extract text from selected pages only

When selecting "Specific Pages", you can specify:

• Individual pages (e.g., "1, 3, 5")

• Ranges (e.g., "1-5")

• A combination of both (e.g., "1-3, 5, 7-9")

Output Format (Optional)

Choose how you want the extracted text to be formatted:

• Plain Text (default): Simple text extraction without preserving layout

• Markdown: Attempts to preserve headings, lists, and basic formatting as markdown

• Structured: Returns JSON with page-by-page text extraction

Output Format

The Convert PDF URL to Text step returns the extracted text in your chosen format:

Plain Text Format (default)

AirOps Platform Updates
January 2025 Edition

Hi there,
We're kicking off the year with updates that streamline how you create and manage content pipelines in AirOps. We've improved our CMS and SERP analytics integrations, introduced more online LLMs, and built smarter troubleshooting helpers to simplify your workflow development. Let's dive in!

WordPress and GSC in the grid
You can now import WordPress blog collections directly into the grid. This new addition joins our existing Webflow integration.
...

Markdown Format

# AirOps Platform Updates
## January 2025 Edition

Hi there,
We're kicking off the year with updates that streamline how you create and manage content pipelines in AirOps. We've improved our CMS and SERP analytics integrations, introduced more online LLMs, and built smarter troubleshooting helpers to simplify your workflow development. Let's dive in!

### WordPress and GSC in the grid
You can now import WordPress blog collections directly into the grid. This new addition joins our existing Webflow integration.
...

Structured Format

{
  "document_info": {
    "title": "Platform Updates",
    "author": "AirOps",
    "pages": 3,
    "created_at": "2025-01-15T10:30:45Z"
  },
  "pages": [
    {
      "page_number": 1,
      "text": "AirOps Platform Updates\nJanuary 2025 Edition\n\nHi there,\nWe're kicking off the year with updates that streamline how you create...",
      "word_count": 245
    },
    {
      "page_number": 2,
      "text": "WordPress and GSC in the grid\nYou can now import WordPress blog collections...",
      "word_count": 312
    },
    {
      "page_number": 3,
      "text": "Fix workflow errors faster with Copilot\nCopilot has been a hit with over 50% of users...",
      "word_count": 189
    }
  ]
}

[IMAGE: Screenshot showing an example of the Convert PDF URL to Text results in the AirOps interface]

How to Use the Results

You can access the extracted text in subsequent workflow steps using Liquid syntax:

{{ step_2.output }}

If you selected the "Structured" format, you can access specific pages:

{{ step_2.output.pages[0].text }}

Common Use Cases

• Extracting content from PDF reports for analysis

• Converting PDF documentation into searchable text

• Feeding PDF content into LLMs for summarization or question-answering

• Creating searchable knowledge bases from PDF collections

• Automating data extraction from PDF forms or invoices

• Analyzing PDF research papers or articles

How to Continue if the Conversion Fails

By default, the Convert PDF URL to Text step will terminate the workflow if it fails. To continue the workflow if the step fails, click "Continue" at the bottom of the settings panel.

[IMAGE: Screenshot showing the "Continue" option in the step settings]

The step will return the following keys when it fails:

• output: this will be null

• error:

  • message: the message returned from the step

  • code: the error code representing the error

Common error causes include:

• Invalid PDF URL

• Inaccessible PDF (requiring authentication or behind a firewall)

• Corrupted PDF file

• Scanned PDFs without OCR

• PDFs with content as images rather than text

Example Workflow

Here's a common pattern using the Convert PDF URL to Text step:

1. Start with a URL to a PDF document (research paper, report, etc.)

2. Use the "Convert PDF URL to Text" step to extract the textual content

3. Use a "Knowledge Base Search" step to find related information in your knowledge base

4. Use an LLM step to analyze or summarize the PDF content with additional context

5. Generate insights, summaries, or answers to specific questions about the document

This workflow enables automated processing of PDF content, allowing you to quickly extract insights from documents without manual review and incorporate that information into your larger knowledge ecosystem.