* RateLimiter: The original TpmRpmLLMLimiter strategy did not account for minute-based rate limiting when scheduled. The RateLimiter was introduced to ensure that the CommunityReportsExtractor could be scheduled to adhere to rate configurations on a per-minute basis.
RateLimiter scheduled: using asyncio and async_mode
Additionally, some key loading issues for rpm = "REQUESTS_PER_MINUTE" and tpm = "TOKENS_PER_MINUTE" were fixed. Configuration loading was also enhanced to include temperature = "TEMPERATURE" and top_p = "TOP_P" settings.
* RateLimiter scheduled: using asyncio and async_mode
* Additionally, some key loading issues for rpm = "REQUESTS_PER_MINUTE" and tpm = "TOKENS_PER_MINUTE" were fixed. Configuration loading was also enhanced to include temperature = "TEMPERATURE" and top_p = "TOP_P" settings.
* Format
* Semversioner
* Format and cleanup
---------
Co-authored-by: Alonso Guevara <alonsog@microsoft.com>
