You can pull text content out of PDF files stored in your base with the 'Extract Text from PDFs' automation. This makes it easy to search, filter, and work with PDF data directly in Airtable.
Setup
Prepare an attachment field containing your PDF files and a long-text field for the extracted text.
Create this automation and select the Airtable base and table you want to use.
Choose the PDF attachment field under Attachments Field, then select the text output under Extracted Text Field.
Review Processing Behavior if the output field already contains values. Only choose to overwrite data you intend to replace.
In Run, limit processing to a view containing one or two test records. Run the automation and compare the extracted text with the original PDF before processing more records.
This extracts text already present in a PDF; it does not read text from scanned images. See PDF text-extraction limits and alternatives for scanned documents, multiple files and output limits. For Word files, use the Word extraction guide instead.