AI Evaluation SDK Ignores Open Telemetry Parent Tracing ID

[BenConstable9]

• Package Name: azure-ai-evaluation
• Package Version: 1.11.0
• Operating System: Linux / Windows
• Python Version: 3.12

Describe the bug
When using the inbuilt evaluators in combination with Open Telemetry OpenAI Instrumentation, parent trace id's are not recorded by the inbuilt evaluators.

To Reproduce
Steps to reproduce the behavior:

from opentelemetry.instrumentation.openai import OpenAIInstrumentor
from opentelemetry import trace
from azure.ai.evaluation import evaluate, RelevanceEvaluator

model_config = {
    "azure_endpoint": os.environ.get("AZURE_OPENAI_ENDPOINT"),
    "api_key": os.environ.get("AZURE_OPENAI_API_KEY"),
    "azure_deployment": os.environ.get("AZURE_OPENAI_DEPLOYMENT"),
}

relevance_evaluator = RelevanceEvaluator(model_config)

tracer = trace.get_tracer("Evaluations")
with tracer.start_as_current_span("TestEvaluations"):
  result = evaluate(
      data="data.jsonl", # provide your data here
      evaluators={
          "relevance": relevance_evaluator
      },
      # column mapping
      evaluator_config={
          "relevance": {
              "column_mapping": {
                  "query": "${data.queries}"
                  "ground_truth": "${data.ground_truth}"
                  "response": "${outputs.response}"
              } 
          }
      }
      # Optionally provide your AI Foundry project information to track your evaluation results in your Azure AI Foundry project
      azure_ai_project = azure_ai_project,
      # Optionally provide an output path to dump a json of metric summary, row level data and metric and AI Foundry URL
      output_path="./evaluation_results.json"
  )

Expected behavior
Expect the span to be attached to any traces emitted by the OpenAI client inside of evaluate.

Instead, traces contain no parent ids so they do not show up in application insights correctly in a timeline.

Screenshots
If applicable, add screenshots to help explain your problem.

Additional context
Add any other context about the problem here.

[github-actions]

Thanks for the feedback! We are routing this to the appropriate team for follow-up. cc @luigiw @needuv @singankit.