The community member is using the create llama app to create a new llamaindex app with FastAPI. They are interested in the new PDF viewer for citations, but it doesn't work because the viewer expects a URL, but the community member is using a local "data" folder with PDFs. They have tried using the DB reader but don't understand how to make it work properly. The community members suggest using an S3 reader to load data directly from an S3 bucket, but it seems to be incompatible with the latest version of Llamaindex. The community members are interested in a tutorial on this approach.
Hey all! I use create llama app to create the scaffolding for a new llamaindex app with FastAPI. I'm interested in the new pdf viewer for the citations. However - it doesn't seem to work in my case, because it's expecting a URL from the response but I have used the data source as "data" folder with pdfs. So it forward the filepath of my linux machine to the frontend and it fails to render the pdf. Has someone got it to work? How would I set this up so I can host the pdfs online and have them be visible? I have tried using the db reader but I don't seem to understand how to make it work properly. Any guides or walkthrus? Thank you
It does require the link. I have a s3 bucket with the pdf sources. But the links are not passed correctly, because I'm using the simpledirectoryreader to ingest data from local /data folder. I want it to work from s3 or wherever allows me to use the docs with pdf viewer. Can you help me out with s3 loader? What steps should I take? Thank you🤠
