…up file

* creacted gptCache class

* added gptcache functionality, in progress

* used a different implementation approch to resolveerrors

* issue retriving from cache when similar prompts

* resolved the errors in caching

* feat: custom auth dependency added

* formatted the code

* formatted the code

* formatted the code

* Delete litellm/tests/test_caching.py

* formatted the code

* removed unwanted code

* removed unwanted code

* removed unwanted code

* removed unwanted code

* removed unwanted code

* resolve conflicts

* fix: resolved dependency issues and cache store issue

* fix: initial api key spend detail taken from db

* formatted using precommit

* formatted using precommit

* formatted code

* feat: budserve middleware to fetch endpoint and project settings and build user_config dictionary and pass it along llm request

* feat: added retrive credential details API in custom auth

* chore: added example env and config for global litellm proxy server

* fix: self.db instead of self.db.db

* cache working fine

* cache working fine

* chore: added budlitellm to gitignore since this is virtual environment

* feat: integrated api call to fetch router config from budserve app

* feat: middleware added to catch exception in middleware and create openai exception object

* chore: cleaned up unused imports

---------

Co-authored-by: budbot <sonali@bud.studio>