Commit Graph

9 Commits

Author SHA1 Message Date
based 861ad18f46 t 2024-05-06 07:10:36 +10:00
based 64c0ad5979 added 11labs support + detect dalle deployments on azure 2024-03-20 00:52:55 +10:00
based 088814edd6 prioritize non filtered models when coming across the same model tier in azure
also reverted the azure checker to being multithreaded instead of asynchronous, the async version does nothing but choke on large key counts even with a small semaphore value. if theres any sort of rate limit in place on something then async is slop.

run_in_executor was also causing timeout errors and ignoring caught exceptions so it's been removed and replaced with the old as_completed method. it gets passed to an executor in the end either way so there shouldn't be much of a performance difference, if any.
2024-01-27 19:21:52 +10:00
based 3ad16793a3 implement a concurrent connection limit so we don't overflow the windows network buffer
(oops)
2024-01-18 12:14:21 +10:00
based 22de3b0754 added async support for various services 2024-01-18 09:14:54 +10:00
based 3edc6f495a test once (dummy) 2024-01-17 04:12:38 +10:00
based aca0be99a7 run filter check on all azure gpt deployments.
blanket fix to catch unfiltered furbo instances, since it's impossible to know if a deployment is running the preview model since we can't get subversions with just an api key
2024-01-07 17:59:47 +10:00
based 039d6c8713 added azure openai support 2023-12-06 10:55:08 +10:00
based 72dd169bac working on azure support 2023-11-24 21:18:47 +10:00