PDF to Text Converter for AI & RAG

Extract clean text and metadata from PDF documents at scale for RAG pipelines, search indexing, and LLM ingestion. Point the actor at any PDF URL and get structured text output without installing local tools. Process entire document libraries in a single run.

Features

• Full text extraction — extracts all readable text from PDF documents using pdf-parse
• Metadata parsing — captures page count, PDF version, author, title, and creation date
• Bulk processing — convert hundreds of PDFs in a single run
• URL-based input — no file uploads needed, just provide URLs pointing to PDF files
• Configurable concurrency — process 1 to 50 PDFs in parallel
• Error resilience — failed documents are reported with error details, not skipped silently

Input

Field	Type	Required	Default	Description
urls	array	Yes	—	List of URLs pointing to PDF files to extract text from
timeoutSeconds	integer	No	30	Maximum seconds to wait for each PDF download
concurrency	integer	No	5	Number of PDFs to process in parallel (1-50)

Input Example

{
  "urls": [
    "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
  ],
  "timeoutSeconds": 30,
  "concurrency": 5
}

Output

Each PDF produces one dataset item containing the extracted text and document metadata.

Key output fields:

• inputUrl (string) — the original PDF URL provided
• status (number) — HTTP status code from the download
• pageCount (number) — number of pages in the PDF
• info (object) — PDF metadata including title, author, creator, producer, and dates
• text (string) — the full extracted text content
• error (string) — error message if extraction failed, otherwise absent

Output Example

{
  "inputUrl": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
  "status": 200,
  "pageCount": 1,
  "info": {
    "Title": "Dummy PDF file",
    "Author": null,
    "Creator": "Writer",
    "Producer": "OpenOffice.org 2.1",
    "CreationDate": "D:20070223175637+02'00'"
  },
  "text": "Dummy PDF file\n\nThis is a dummy PDF file for testing purposes."
}

Pricing

Event	Cost
Document Converted	Pay-per-event (see actor pricing page)

The actor respects the per-run max charge limit. Processing stops automatically when the spending cap is reached.

Use Cases

• RAG document ingestion — extract text from PDF knowledge bases for vector database indexing
• Search indexing — make PDF content searchable by extracting and indexing the text
• Compliance review — bulk-extract text from policy documents and contracts for automated analysis
• Academic research — convert research papers to plain text for NLP processing and citation analysis
• Data migration — extract content from legacy PDF archives into structured text formats

Related Actors

Actor	What it adds
Web Page to Markdown Converter for LLMs	Convert web pages to Markdown alongside your PDF pipeline
Article Text Extractor for TTS & AI	Extract article text from web pages for a complete content pipeline
HTML Table Extractor	Extract structured table data from web pages