feat: Add OpenAI Rate limiting (#1805)

* Implement adaptive rate limiter for OpenAI

* Add adaptive rate limiter to Bedrock model

* Use a sensible default maximum request rate

* Ruff 🐶

* Mark test as xfail after llama_index update

* Do not retry on rate limit errors with tenacity

* Remove xfail after llama_index version lock

* Use events and locks instead of nesting asyncio.run

* Ensure that events are always set after rate limit handling

* Retry on httpx ReadTimeout errors

* Update rate limiters with verbose generation info

* Improve end of queue handling in AsyncExecutor

* improve types to remove the need for casts (#1817)

* Improve interrupt handling

* Exit early from queue.join on termination events

* Properly cancel running tasks

* Add pytest-asyncio to hatch env

* Do not await cancelled tasks

* Improve task_done marking logic

* Increase default concurrency

---------

Co-authored-by: Xander Song <axiomofjoy@gmail.com>