hustledustle

Sorry for the late response. Here's one of the files.

acloud_get_st.pdf

Here it is

acloud_acloud_conn_rl_mq_conn_1_0.pdf

debugging the pdf.go execution, it appears that "github.com/ledongthuc/pdf" is picking up invisible characters

Issue is in the PDFs, I manually opened the one I shared here with Wondershare PDfelement, resaving it fixed the issue. Its some type of character Swift adds for some reason 🙂

Hi everyone, im currently making my own chat bot based on PDFs. I was able to vectorize them but when I chat with the bot using a local model, some of the words are surrounded with CC
And when I check the logs, I see the chunks of text where words are surrounded with Cs. Any idea how I can remove this? I used Openai's text-embedding-3-large.