Fixes for safety provider added to nvidia distro

llama_stack/templates/nvidia/build.yaml

@@ -7,7 +7,7 @@ distribution_spec:
     vector_io:
     - inline::faiss
     safety:
-    - inline::llama-guard
+    - remote::nvidia
     agents:
     - inline::meta-reference
     telemetry:
@@ -15,16 +15,9 @@ distribution_spec:
     eval:
     - inline::meta-reference
     datasetio:
-    - remote::huggingface
     - inline::localfs
     scoring:
     - inline::basic
-    - inline::llm-as-judge
-    - inline::braintrust
     tool_runtime:
-    - remote::brave-search
-    - remote::tavily-search
-    - inline::code-interpreter
     - inline::rag-runtime
-    - remote::model-context-protocol
 image_type: conda

llama_stack/templates/nvidia/nvidia.py

@@ -79,7 +79,7 @@ def get_distribution_template() -> DistributionTemplate:
     return DistributionTemplate(
         name="nvidia",
         distro_type="remote_hosted",
-        description="Use NVIDIA NIM for running LLM inference",
+        description="Use NVIDIA NIM for running LLM inference and safety",
         container_image=None,
         template_path=Path(__file__).parent / "doc_template.md",
         providers=providers,
@@ -100,7 +100,7 @@ def get_distribution_template() -> DistributionTemplate:
                     ]
                 },
                 default_models=[inference_model, safety_model],
-                default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
+                default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
                 default_tool_groups=default_tool_groups,
             ),
         },

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

@@ -31,8 +31,8 @@ providers:
         namespace: null
         db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
   safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
+  - provider_id: nvidia
+    provider_type: remote::nvidia
     config: {}
   agents:
   - provider_id: meta-reference
@@ -54,9 +54,6 @@ providers:
     provider_type: inline::meta-reference
     config: {}
   datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config: {}
   - provider_id: localfs
     provider_type: inline::localfs
     config: {}
@@ -64,33 +61,10 @@ providers:
   - provider_id: basic
     provider_type: inline::basic
     config: {}
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-    config: {}
-  - provider_id: braintrust
-    provider_type: inline::braintrust
-    config:
-      openai_api_key: ${env.OPENAI_API_KEY:}
   tool_runtime:
-  - provider_id: brave-search
-    provider_type: remote::brave-search
-    config:
-      api_key: ${env.BRAVE_SEARCH_API_KEY:}
-      max_results: 3
-  - provider_id: tavily-search
-    provider_type: remote::tavily-search
-    config:
-      api_key: ${env.TAVILY_SEARCH_API_KEY:}
-      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
   - provider_id: rag-runtime
     provider_type: inline::rag-runtime
     config: {}
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
@@ -105,16 +79,13 @@ models:
   model_type: llm
 shields:
 - shield_id: ${env.SAFETY_MODEL}
+  provider_id: nvidia
 vector_dbs: []
 datasets: []
 scoring_fns: []
 benchmarks: []
 tool_groups:
-- toolgroup_id: builtin::websearch
-  provider_id: tavily-search
 - toolgroup_id: builtin::rag
   provider_id: rag-runtime
-- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
 server:
   port: 8321

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

@@ -110,8 +110,7 @@ models:
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
-  provider_id: ollama
-  provider_model_id: all-minilm:latest
+  provider_id: sentence-transformers
   model_type: embedding
 shields:
 - shield_id: ${env.SAFETY_MODEL}

llama_stack/templates/ollama/run.yaml

@@ -103,8 +103,7 @@ models:
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
-  provider_id: ollama
-  provider_model_id: all-minilm:latest
+  provider_id: sentence-transformers
   model_type: embedding
 shields: []
 vector_dbs: []