chore(llmobs): fix telemetry namespace for ragas (#11279)

`ml_obs` is the correct namespace for llmobs that's been implemented in
the telemetry backend

update ragas telemetry metrics to use that namespace

## Checklist
- [x] PR author has checked that all the criteria below are met
- The PR description includes an overview of the change
- The PR description articulates the motivation for the change
- The change includes tests OR the PR description describes a testing
strategy
- The PR description notes risks associated with the change, if any
- Newly-added code is easy to change
- The change follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
- The change includes or references documentation updates if necessary
- Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

## Reviewer Checklist
- [x] Reviewer has checked that all the criteria below are met 
- Title is accurate
- All changes are related to the pull request's stated goal
- Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- Testing strategy adequately addresses listed risks
- Newly-added code is easy to change
- Release note makes sense to a user of the library
- If necessary, author has acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment
- Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

Co-authored-by: lievan <[email protected]>

ddtrace/llmobs/_evaluators/ragas/faithfulness.py

@@ -7,6 +7,7 @@
 
 from ddtrace.internal.logger import get_logger
 from ddtrace.internal.telemetry import telemetry_writer
+from ddtrace.internal.telemetry.constants import TELEMETRY_APM_PRODUCT
 from ddtrace.internal.telemetry.constants import TELEMETRY_LOG_LEVEL
 from ddtrace.internal.utils.version import parse_version
 from ddtrace.llmobs._constants import RAGAS_ML_APP_PREFIX
@@ -138,7 +139,7 @@ def __init__(self, llmobs_service):
             raise NotImplementedError("Failed to load dependencies for `ragas_faithfulness` evaluator") from e
         finally:
             telemetry_writer.add_count_metric(
-                namespace="llmobs",
+                namespace=TELEMETRY_APM_PRODUCT.LLMOBS,
                 name="evaluators.init",
                 value=1,
                 tags=(
@@ -164,7 +165,7 @@ def run_and_submit_evaluation(self, span_event: dict):
             return
         score_result_or_failure = self.evaluate(span_event)
         telemetry_writer.add_count_metric(
-            "llmobs",
+            TELEMETRY_APM_PRODUCT.LLMOBS,  # type: ignore
             "evaluators.run",
             1,
             tags=(

ddtrace/llmobs/_evaluators/runner.py

@@ -7,6 +7,7 @@
 from ddtrace.internal.logger import get_logger
 from ddtrace.internal.periodic import PeriodicService
 from ddtrace.internal.telemetry import telemetry_writer
+from ddtrace.internal.telemetry.constants import TELEMETRY_APM_PRODUCT
 from ddtrace.llmobs._evaluators.ragas.faithfulness import RagasFaithfulnessEvaluator
 from ddtrace.llmobs._evaluators.sampler import EvaluatorRunnerSampler
 
@@ -55,7 +56,7 @@ def __init__(self, interval: float, llmobs_service=None, evaluators=None):
                     raise e
                 finally:
                     telemetry_writer.add_count_metric(
-                        namespace="llmobs",
+                        namespace=TELEMETRY_APM_PRODUCT.LLMOBS,  # type: ignore
                         name="evaluators.init",
                         value=1,
                         tags=(

ddtrace/llmobs/_evaluators/sampler.py

@@ -8,6 +8,7 @@
 from ddtrace import config
 from ddtrace.internal.logger import get_logger
 from ddtrace.internal.telemetry import telemetry_writer
+from ddtrace.internal.telemetry.constants import TELEMETRY_APM_PRODUCT
 from ddtrace.internal.telemetry.constants import TELEMETRY_LOG_LEVEL
 from ddtrace.sampling_rule import SamplingRule
 
@@ -66,7 +67,7 @@ def parsing_failed_because(msg, maybe_throw_this):
                 TELEMETRY_LOG_LEVEL.ERROR, message="Evaluator sampling parsing failure because: {}".format(msg)
             )
             telemetry_writer.add_count_metric(
-                namespace="llmobs",
+                namespace=TELEMETRY_APM_PRODUCT.LLMOBS,
                 name="evaluators.error",
                 value=1,
                 tags=(("reason", "sampling_rule_parsing_failure"),),
@@ -103,7 +104,7 @@ def parsing_failed_because(msg, maybe_throw_this):
             span_name = rule.get(EvaluatorRunnerSamplingRule.SPAN_NAME_KEY, SamplingRule.NO_RULE)
             evaluator_label = rule.get(EvaluatorRunnerSamplingRule.EVALUATOR_LABEL_KEY, SamplingRule.NO_RULE)
             telemetry_writer.add_distribution_metric(
-                "llmobs",
+                TELEMETRY_APM_PRODUCT.LLMOBS,  # type: ignore
                 "evaluators.rule_sample_rate",
                 sample_rate,
                 tags=(("evaluator_label", evaluator_label), ("span_name", span_name)),