Question

Knowledgebases indexing 0 tokens (or far less than the data provided)

Posted on May 1, 2025
Databases Managed Databases AI/ML Database Dev/Management
Asked by setec

Has anyone else ran into the situation where a knowledgebase reports “success” after indexing 0 tokens (or a small number of tokens far less than the source added)?

If so have you found a fix?

Submit an answer

This textbox defaults to using Markdown to format your answer.

You can type !ref in this text area to quickly search our full set of tutorials, documentation & marketplace offerings and insert the link!

These answers are provided by our Community. If you find them useful, show some love by clicking the heart. If you run into issues leave a comment, or add your own answer to help others.

Bobby Iliev

Site Moderator

• May 2, 2025

Hey @setec,

I think I’ve seen something like this before. In my case, it happened when the file looked fine but didn’t actually have much plain text, like a PDF with scanned images or weird formatting. The system showed ‘success’ but indexed 0 tokens or way fewer than expected.

It might also happen if the file is too small, or maybe the content isn’t in a format the indexer can handle well. Not 100% sure, but re-uploading as a plain .txt or .md file seemed to help when I ran into it.

Could also be something with the way the knowledgebase processes links or encodings, just guessing here though. It might be best to reach out to support if you are still seeing this: https://do.co/support

- Bobby