Merge branch 'main' into nvidia-e2e-notebook

llama_stack/distribution/routers/routing_tables.py

@@ -439,8 +439,8 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
 
         # infer provider from source
         if metadata:
-            if metadata.get("provider"):
-                provider_id = metadata.get("provider")  # pass through from nvidia datasetio
+            if metadata.get("provider_id"):
+                provider_id = metadata.get("provider_id")  # pass through from nvidia datasetio
         elif source.type == DatasetType.rows.value:
             provider_id = "localfs"
         elif source.type == DatasetType.uri.value:

llama_stack/providers/remote/datasetio/nvidia/datasetio.py

@@ -44,8 +44,7 @@ class NvidiaDatasetIOAdapter:
             request_headers.update(headers)
 
         async with aiohttp.ClientSession(headers=request_headers) as session:
-            # TODO: Remove `verify_ssl=False`. Added for testing purposes to call NMP int environment from `docs/notebooks/nvidia/`
-            async with session.request(method, url, params=params, json=json, verify_ssl=False, **kwargs) as response:
+            async with session.request(method, url, params=params, json=json, **kwargs) as response:
                 if response.status != 200:
                     error_data = await response.json()
                     raise Exception(f"API request failed: {error_data}")

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
@@ -38,6 +39,11 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="remote::nvidia",
         config=NVIDIASafetyConfig.sample_run_config(),
     )
+    datasetio_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NvidiaDatasetIOConfig.sample_run_config(),
+    )
     eval_provider = Provider(
         provider_id="nvidia",
         provider_type="remote::nvidia",
@@ -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.yaml

@@ -62,13 +62,6 @@ 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
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
   - provider_id: nvidia
     provider_type: remote::nvidia
     config: