add datasetio to distribution

llama_stack/templates/nvidia/build.yaml

@@ -18,6 +18,7 @@ distribution_spec:
     - remote::nvidia
     datasetio:
     - inline::localfs
+    - remote::nvidia
     scoring:
     - inline::basic
     tool_runtime:

llama_stack/templates/nvidia/nvidia.py

@@ -7,6 +7,7 @@
 from pathlib import Path
 
 from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
+from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
 from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
@@ -23,7 +24,7 @@ def get_distribution_template() -> DistributionTemplate:
         "telemetry": ["inline::meta-reference"],
         "eval": ["remote::nvidia"],
         "post_training": ["remote::nvidia"],
-        "datasetio": ["inline::localfs"],
+        "datasetio": ["inline::localfs", "remote::nvidia"],
         "scoring": ["inline::basic"],
         "tool_runtime": ["inline::rag-runtime"],
     }
@@ -51,6 +52,11 @@ def get_distribution_template() -> DistributionTemplate:
         model_id="${env.SAFETY_MODEL}",
         provider_id="nvidia",
     )
+    datasetio_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NvidiaDatasetIOConfig.sample_run_config(),
+    )
 
     available_models = {
         "nvidia": MODEL_ENTRIES,
@@ -75,6 +81,7 @@ def get_distribution_template() -> DistributionTemplate:
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
+                    "datasetio": [datasetio_provider],
                     "eval": [eval_provider],
                 },
                 default_models=default_models,

llama_stack/templates/nvidia/run-with-safety.yaml

@@ -74,6 +74,13 @@ providers:
         type: sqlite
         namespace: null
         db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:}
+      user_id: ${env.NVIDIA_USER_ID:llama-stack-user}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
   scoring:
   - provider_id: basic
     provider_type: inline::basic

llama_stack/templates/nvidia/run.yaml

@@ -62,13 +62,13 @@ providers:
       project_id: ${env.NVIDIA_PROJECT_ID:test-project}
       customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
   datasetio:
-  - provider_id: localfs
-    provider_type: inline::localfs
+  - provider_id: nvidia
+    provider_type: remote::nvidia
     config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
+      api_key: ${env.NVIDIA_API_KEY:}
+      user_id: ${env.NVIDIA_USER_ID:llama-stack-user}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
   scoring:
   - provider_id: basic
     provider_type: inline::basic