Skip to main content
Document & PDF Search

Your PDFs, finally answering questions

Menus, price lists, agendas, handbooks and forms often live in PDFs nobody opens. GoChatterBot reads the text inside the documents in your Media Library and answers from them, with a link to the file.

  • Text inside PDFs
  • Links to the document
  • New uploads read automatically

How it works

Upload as usual. Visitors just ask.

Upload to the Media Library

Add PDFs the way you always do, or keep the ones already there.

Text is read in the background

The plugin pulls the text out of each PDF on your own site, a few at a time.

Answers cite the document

When a PDF holds the answer, the chatbot quotes it and links to the file.

Made for

The documents people ask about most

Agendas & minutes“What’s on Tuesday’s agenda?”
Price lists“How much is a room rental?”
Handbooks“Can I pause my membership?”
Forms & guides“What do I need to apply?”
Menus & catalogs“Do you have vegan options?”

Three ticks

Turn it on in Settings → Content

Let the chatbot read documents in your Media Library, skip photos, and read the text inside PDFs. The settings page shows how many of your PDFs have text it can read and which are still waiting.

  • Read PDFs nowCatches up on a large library straight away, then keeps going in the background.
  • Searches include PDF textTurn on “Let searches match the fields and PDF text” and a question can find a PDF by its contents, not just its title.
What the chatbot reads
Documents
Read documents in the Media LibraryDocuments only, not photos and other imagesRead the text inside PDFs18 of 20 PDFs have text the chatbot can read. Scanned pages without a text layer cannot be read.
PDF text fromRead the PDFs here
Read PDFs now

Example numbers. Your settings page shows your own library.

About scanned documents: a scan without a text layer is only a picture, so there is nothing to read. Re-saving it with text recognition (most scanner software and PDF editors can do this) makes it readable.
A laptop on a desk beside printed documents and a plant

From paper to answers

The documents on your desk, answerable online

Price lists, forms and handbooks usually start as documents. Upload them to your Media Library as PDFs with text, and the chatbot can quote them and link to the file.

  • Read in the backgroundNew uploads are read automatically.
  • Linked in answersVisitors can open the full document.

Frequently asked questions

Which documents can the chatbot read?

Documents in your WordPress Media Library. For PDFs it reads the text inside the file, so an answer can come from page 12 of your handbook, and the answer links to the document.

What about scanned PDFs?

A scanned page is a picture of text. Unless the PDF has a text layer (most scanners and “Save as PDF” add one; some older scans don’t), there is no text to read. The Content settings show how many of your PDFs have readable text.

Do I need to do anything when I upload a new PDF?

No. New PDFs are read in the background. To catch up on a large library straight away, use Read PDFs now in Settings → Content; it reads a few at once and the rest in the background.

Will it read photos and images in the Media Library too?

Tick Documents only, not photos and other images and it skips them, so answers come from real documents.

My host can’t read PDFs. Is there another way?

Reading PDFs directly needs a common server tool called Ghostscript, and the settings page tells you if it is missing. If another plugin already stores each PDF’s text in a custom field, enter that field’s name under PDF text from and the chatbot uses it instead.

Put your PDFs to work

Turn on document reading and your chatbot answers from the files in your Media Library.

Free plan: 1 website and 100 chatbot replies a month.