GenAi metrics TTFT/TPOT histogram SHOULD be specified with ExplicitBucketBoundaries

[qwtsc]

Describe your environment

any env

What happened?

def create_gen_ai_server_time_per_output_token(meter: Meter) -> Histogram:
    """Time per output token generated after the first token for successful responses"""
    return meter.create_histogram(
        name=GEN_AI_SERVER_TIME_PER_OUTPUT_TOKEN,
        description="Time per output token generated after the first token for successful responses.",
        unit="s",
    )

def create_gen_ai_server_time_to_first_token(meter: Meter) -> Histogram:
    """Time to generate first token for successful responses"""
    return meter.create_histogram(
        name=GEN_AI_SERVER_TIME_TO_FIRST_TOKEN,
        description="Time to generate first token for successful responses.",
        unit="s",
    )

these two help methods are not correctly implemented, because the related semconv states SHOULD be specified with ExplicitBucketBoundaries .... The histogram created from these two methods would use _DEFAULT_EXPLICIT_BUCKET_HISTOGRAM_AGGREGATION_BOUNDARIES, which is totally wrong and meaningless for ttft and tpot.

Steps to Reproduce

code issue.

Expected Result

code issue.

Actual Result

code issue.

Additional context

No response

Would you like to implement a fix?

Yes

Tip

_{React with 👍 to help prioritize this issue. Please use comments to provide useful context, avoiding +1 or me too, to help us triage it. Learn more here.}

[alliasgher]

Opened #5084 for this.