feat(evaluator): inline + hybrid metric bundlers; built-ins skip cloudpickle

docs/evaluator/index.mdx

@@ -59,7 +59,6 @@ Submit your evaluation to the Evaluator service using the NeMo Platform SDK:
 
 ```python
 from nemo_evaluator.sdk import Evaluator
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 from nemo_platform import NeMoPlatform
 
 
@@ -74,7 +73,6 @@ job = evaluator.submit(
     metric=metric,
     dataset=dataset,
     config=config,
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()

docs/evaluator/metrics/agent-configuration.mdx

@@ -164,7 +164,6 @@ from nemo_evaluator_sdk import Agent, RunConfigOnline
 
 
 from nemo_evaluator_sdk import ExactMatchMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 metric = ExactMatchMetric(reference="{{item.expected_answer}}")
 agent = Agent(
     url="https://my-nat-agent.example.com",
@@ -185,7 +184,6 @@ job = evaluator.submit(
             {"role": "user", "content": "{{item.question}}"},
         ],
     },
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()

docs/evaluator/metrics/agentic.mdx

@@ -228,7 +228,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfig
 from nemo_evaluator_sdk.metrics.ragas import ToolCallAccuracyMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 metric = ToolCallAccuracyMetric()
 
 job = evaluator.submit(
@@ -251,7 +250,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -430,7 +428,6 @@ print(result.aggregate_scores)
 
 ```python
 from nemo_evaluator_sdk import RunConfig, ToolCallingMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 metric = ToolCallingMetric(reference="{{item.tool_calls}}")
 
@@ -465,7 +462,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -572,7 +568,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfig, Model
 from nemo_evaluator_sdk.metrics.ragas import TopicAdherenceMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 judge_model = Model(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
@@ -596,7 +591,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -768,7 +762,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfig, Model
 from nemo_evaluator_sdk.metrics.ragas import AgentGoalAccuracyMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 judge_model = Model(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
@@ -798,7 +791,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -925,7 +917,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfig, Model
 from nemo_evaluator_sdk.metrics.ragas import AgentGoalAccuracyMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 judge_model = Model(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
@@ -963,7 +954,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -1023,7 +1013,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfig, Model
 from nemo_evaluator_sdk.metrics.ragas import AnswerAccuracyMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 judge_model = Model(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
@@ -1042,7 +1031,6 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -1055,7 +1043,6 @@ print(result.aggregate_scores)
 ```python
 from nemo_evaluator_sdk import RunConfigOnlineModel, InferenceParams, Model
 from nemo_evaluator_sdk.metrics.ragas import AnswerAccuracyMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 judge_model = Model(
     url="https://integrate.api.nvidia.com/v1/chat/completions",
@@ -1090,7 +1077,6 @@ job = evaluator.submit(
             }
         ]
     },
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 
 job.wait_until_done()

docs/evaluator/metrics/job-management.mdx

@@ -21,7 +21,6 @@ from nemo_evaluator.sdk import Evaluator
 from nemo_platform import NeMoPlatform
 from nemo_evaluator_sdk import RunConfig
 from nemo_evaluator_sdk import ExactMatchMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 sdk = NeMoPlatform(
     base_url=os.environ.get("NMP_BASE_URL", "http://localhost:8080"),
@@ -38,7 +37,6 @@ job = evaluator.submit(
         {"expected": "Berlin", "output": "Munich"},
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 print("Submitted job:", job.name)
 

docs/evaluator/metrics/llm-as-a-judge.mdx

@@ -298,7 +298,6 @@ For production workloads, submit the same metric and dataset as a durable platfo
 
 ```python
 from nemo_evaluator_sdk import RunConfig, JSONScoreParser, Model, RubricScore, LLMJudgeMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 metric = LLMJudgeMetric(
     model=Model(
@@ -347,7 +346,6 @@ job = evaluator.submit(
         {"input": "What is 2 + 2?", "output": "4"},
     ],
     config=RunConfig(parallelism=8, limit_samples=100),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 print("Submitted job:", job.name)
 
@@ -436,13 +434,13 @@ By default, the JSON parser is used for range and rubric scores, with the score
 
 ```python
 # JSON parser (default)
-"parser": {"type": "json", "json_path": "quality"}
+parser = {"type": "json", "json_path": "quality"}
 
 # Regex parser (for models that do not support structured output)
-"parser": {"type": "regex", "pattern": "QUALITY: (\\w+)"}
+parser = {"type": "regex", "pattern": "QUALITY: (\\w+)"}
 
 # Regex parser with method='search' (finds pattern anywhere in text)
-"parser": {"type": "regex", "pattern": "SCORE: (\\d+)", "method": "search"}
+parser = {"type": "regex", "pattern": "SCORE: (\\d+)", "method": "search"}
 ```
 
 <Tip>
@@ -642,15 +640,13 @@ metric = {
 Control judge model behavior with inference parameters:
 
 ```python
-
-"prompt_template": {
+prompt_template = {
     "messages": [...],
-    "temperature": 0.1, # Lower for more consistent scoring
-    "max_tokens": 1024, # Increase if judge needs more space
-    "timeout": 30, # Request timeout in seconds
-    "stop": ["<{{ end_of_text }}>"] # Stop sequences
+    "temperature": 0.1,  # Lower for more consistent scoring
+    "max_tokens": 1024,  # Increase if judge needs more space
+    "timeout": 30,  # Request timeout in seconds
+    "stop": ["<end_of_text>"],  # Stop sequences
 }
-
 ```
 
 <Note>

docs/evaluator/metrics/manage-metrics.mdx

@@ -98,7 +98,6 @@ For online evaluations, provide a model or agent target and use the online param
 
 ```python
 from nemo_evaluator_sdk import RunConfig, ExactMatchMetric
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 metric = ExactMatchMetric(reference="{{item.expected}}", candidate="{{item.output}}")
 
@@ -109,7 +108,6 @@ job = evaluator.submit(
         {"expected": "Berlin", "output": "Munich"},
     ],
     config=RunConfig(parallelism=4),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 
 job.wait_until_done()

docs/evaluator/metrics/model-configuration.mdx

@@ -208,14 +208,12 @@ Durable remote `evaluator.submit(...)` jobs additionally accept a `ModelRef` tar
 
 ```python
 from nemo_evaluator_sdk import ModelRef, RunConfigOnlineModel
-from nemo_evaluator.shared.metric_bundles.cloudpickle import CloudpickleMetricBundlePackager
 
 job = evaluator.submit(
     metric=metric,
     dataset=dataset,
     config=RunConfigOnlineModel(),
     target=ModelRef(root="default/my-model"),
-    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 ```