Account for `retry-after-ms` header

[simonkurtz-MSFT]

Presently, the module only accounts for the retry-after header containing a value in seconds. Azure OpenAI Provisioned Throughput (PTU) deployments also pass back the retry-after-ms header containing a value in milliseconds. This value may be preferential to seconds.

From the PTU documentation:

*A 429 response indicates that the allocated PTUs are fully consumed at the time of the call. The response includes the retry-after-ms and retry-after headers that tell you the time to wait before the next call will be accepted. *

As such, there is only a longer delay when not using retry-after-ms when there is simply no PTU left to consume (overall and/or tokens-per-minute?). This may be an acceptable situation that may not surface too often.

---

One approach may be to convert everything internal to the module to milliseconds. These resources provide the starting point for the enhancement:

• https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/provisioned-get-started#handling-high-utilization
• honor retry-after-ms for azure clients openai/openai-python#1046

cc @kristapratico