docs(evaluator): fix submit() packager, FilesetRef import, and leaked titles

docs/evaluator/index.mdx

@@ -59,6 +59,7 @@ 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
 
 
@@ -69,7 +70,12 @@ evaluator: Evaluator = sdk.evaluator
 local_result = evaluator.run(metric=metric, dataset=dataset, config=config)
 
 # Production evaluation as a durable platform job
-job = evaluator.submit(metric=metric, dataset=dataset, config=config)
+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

@@ -164,6 +164,7 @@ 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",
@@ -184,6 +185,7 @@ 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

@@ -228,6 +228,7 @@ 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(
@@ -250,6 +251,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -428,6 +430,7 @@ 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}}")
 
@@ -462,6 +465,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -568,6 +572,7 @@ 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",
@@ -591,6 +596,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -762,6 +768,7 @@ 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",
@@ -791,6 +798,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -917,6 +925,7 @@ 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",
@@ -954,6 +963,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -1013,6 +1023,7 @@ 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",
@@ -1031,6 +1042,7 @@ job = evaluator.submit(
         }
     ],
     config=RunConfig(parallelism=4),
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 job.wait_until_done()
 result = job.get_result()
@@ -1043,6 +1055,7 @@ 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",
@@ -1077,6 +1090,7 @@ job = evaluator.submit(
             }
         ]
     },
+    metric_bundle_packager=CloudpickleMetricBundlePackager(),
 )
 
 job.wait_until_done()

docs/evaluator/metrics/job-management.mdx

@@ -21,6 +21,7 @@ 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"),
@@ -37,6 +38,7 @@ 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

@@ -298,6 +298,7 @@ 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(
@@ -346,6 +347,7 @@ 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)
 

docs/evaluator/metrics/manage-metrics.mdx

@@ -98,6 +98,7 @@ 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}}")
 
@@ -108,6 +109,7 @@ 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

@@ -183,7 +183,43 @@ Use plain `RunConfig` for offline evaluations where the dataset already contains
 
 ## Model References
 
-The plugin SDK examples on this page use inline `Model` objects. If your deployment resolves platform model entities into model endpoint details, perform that lookup before constructing the `Model`, then pass the resulting inline model to the metric or request.
+You can supply the evaluation target two ways. Which one is valid depends on whether you run the evaluation locally or submit it as a durable platform job.
+
+### Inline `Model` (required for `evaluator.run(...)`)
+
+`evaluator.run(...)` executes in your local Python process, so it needs the resolved endpoint details inline. Always pass an inline `Model` as the `target` (or as a judge/embeddings field on the metric). If your deployment stores platform model entities, resolve the entity into endpoint details before constructing the `Model`:
+
+```python
+from nemo_evaluator_sdk import Model
+
+model_entity = client.models.retrieve("my-model", workspace="default")
+model = Model(
+    url=client.models.get_model_entity_route_openai_url(model_entity),
+    name="my-model",
+    api_key_secret="NVIDIA_API_KEY",
+)
+
+result = evaluator.run(metric=metric, dataset=dataset, target=model)
+```
+
+### `ModelRef` (supported by `evaluator.submit(...)`)
+
+Durable remote `evaluator.submit(...)` jobs additionally accept a `ModelRef` target. A `ModelRef` names a platform model entity (`workspace/model-name`) and is resolved by the evaluator backend when the job runs, so you do not have to resolve the endpoint yourself. Use this for platform-managed model routing. A `ModelRef` target generates outputs online, so it requires an online run config (`RunConfigOnlineModel`):
+
+```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(),
+)
+```
+
+`ModelRef` is **not** valid for `evaluator.run(...)`; the local runtime cannot resolve a platform entity. Pass an inline `Model` for local runs and either a `Model` or a `ModelRef` for remote submits. See the [Define and Run Custom Python Metrics](/documentation/evaluate-models/tutorials/define-and-run-custom-python-metrics) tutorial for an end-to-end `ModelRef` + `FilesetRef` submit example.
 
 <Note>