The community members are discussing whether it is possible to have llamaIndex load PDFs directly from an S3 bucket without first downloading the bucket contents locally. The initial response suggests that it may not be possible, but that a custom loader could be written. Another community member mentions that the GitHub repo loader might be able to do something similar, but they couldn't figure it out. One community member tried using a loader from llamahub, but encountered an error about the resource being permanently moved. After some troubleshooting, they were able to resolve the issue by using the "prefix" parameter instead of "key" and specifying the S3 endpoint URL.
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?
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 😆
