deepset-ai
New tutorial for: configurable elasticsearchdocumentstore
Describe the tutorial you would like to see here All the current tutorials assume the document store will not change over time.
For example, assume we have a single elastic database engine and need to build a single application where each user should ask a question and retrieve an answer. However, each user should have access to a different index "database" on the elastic search. The current implementation assumes a fixed document store information during application run-time, like : https://github.com/deepset-ai/haystack-tutorials/blob/main/tutorials/03_Scalable_QA_System.ipynb
It would be beneficial to have a tutorial where we can change the document store username, password, and index during application runtime. Otherwise, we must build a duplicate application for each user and each index.
Additional context None
[X] I've checked the existing tutorials
Hi @agemagician 👋 thank you for opening the issue. You have a nice problem here. Unfortunately, you cannot change username and password during the runtime. You can change the index but it will require re-connecting every time you change it. I would recommend creating different DocumentStores rather than changing the credentials altogether. Another idea could be using metadata filtering and let Elastic handle the user management.
