New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

bug(api): Sometimes PDF contents gets mangled on extraction #1150

Open

CollectiveUnicorn opened this issue Sep 25, 2024 · 0 comments

Labels

api possible-bug 🐛

Contributor

CollectiveUnicorn commented Sep 25, 2024

Steps to reproduce

Download a PDF like the one attached here: aesopsfables00aeso.pdf
Upload the PDF to using the API
Create a new vector store or update an existing one using the PDF
Wait for the vector indexing to complete
Observe in the DB that the content is missing spaces between words.

Expected result

The content piece of the vector_content has spaces so that when given to the LLM the text is intelligible.

Actual Result

The content piece of the vector_content does not have spaces, so the LLM gets a glob of text.

Visual Proof (screenshots, videos, text, etc)

Additional Context

This does not happen for all PDFs only some of them.

The text was updated successfully, but these errors were encountered:

CollectiveUnicorn added the possible-bug 🐛 label

nywilken added the api label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment