Find answers from the community

Updated 3 months ago

Hi

Hi
Is it inately possible to have llamaIndex load pdfs from an s3 bucket without we having to download the bucket contents locally then reading from there?

7 comments

LLogan M

hmmm I don't think its possible? Youd definitely have to write your own loader though (which tbh is not too hard or scary)

LLogan M

I feel like the github repo loader does something like that, but I can't figure it out at a glance

TTurner

I tried one of the loaders on llamahub
https://llamahub.ai/l/readers/llama-index-readers-s3?from=readers

but i think I run into an error that said the resource has been permanently moved
let me find the exact error message

TTurner

Attachment

LLogan M

google tells me this is an issue with your region name or other credentials? 👀

TTurner

hmm weird, i used same credentials to download files through the CLI though 💀

TTurner

ah resolved it XD
went through the class definition and found out I was supposed to use "prefix" instead of "key", and had to specify the s3_endpoint_url 😆

Add a reply