Hello,
I want to create a search based chatbot based on users files it can be pdf, txt, rft, etc some question around that are

1. In an environment like AWS should a vector db be used like(qdrant) or we just create index for each user as we have a multi tenant system?
2. Can we load index in or load from some thing like AWS S3, EFS etc
3. If we use Qdrant can we specify metadata like userid so we dont create too many index(collections) in vector db but rather define filter when querying so that only document specific to user are extracted
4. If we are querying pdf, txt how can we get source page no, line no, references etc

Hi,
Can we dynamically load and unload indices as I want system to be multi tenant and different users data should be in separate index for isolation and security.

Hello,
New here I want to build a search engine like a QnA bot a user can have files like pdf, txt, words etc. Then he/she could question and bot should be able to answer and specify source files etc for more details, how can i achieve this as many users be uploading files a cannot load full index in memory to server if for example each user has 1 GB of data for n number of users.

Can we build and do code analysis of codebase and we could query, like how login works(and it should provide all files included that are used to build login feature), what trying build is

1. Get linkage or branches of files and function
2. Question like (how is auth done? Explain me how to create new user? etc)

Not simple question like where can I find X
@Logan M