Merge branch 'main' of https://github.com/meta-llama/llama-stack into add_nemo_customizer

llama_stack/templates/nvidia/build.yaml

@@ -1,13 +1,15 @@
 version: '2'
 distribution_spec:
-  description: Use NVIDIA NIM for running LLM inference
+  description: Use NVIDIA NIM for running LLM inference and safety
   providers:
     inference:
     - remote::nvidia
     vector_io:
     - inline::faiss
     safety:
-    - inline::llama-guard
+    - remote::nvidia
+    post_training:
+    - remote::nvidia
     agents:
     - inline::meta-reference
     telemetry:
@@ -15,18 +17,9 @@ distribution_spec:
     eval:
     - inline::meta-reference
     datasetio:
-    - remote::huggingface
     - inline::localfs
     scoring:
     - inline::basic
-    - inline::llm-as-judge
-    - inline::braintrust
-    post_training:
-    - remote::nvidia
     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/doc_template.md

@@ -20,7 +20,7 @@ The following environment variables can be configured:
 The following models are available by default:
 
 {% for model in default_models %}
-- `{{ model.model_id }} ({{ model.provider_model_id }})`
+- `{{ model.model_id }} {{ model.doc_string }}`
 {% endfor %}
 {% endif %}
 

llama_stack/templates/nvidia/nvidia.py

@@ -6,32 +6,26 @@
 
 from pathlib import Path
 
-from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
-from llama_stack.models.llama.sku_list import all_registered_models
+from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
-from llama_stack.providers.remote.inference.nvidia.models import _MODEL_ENTRIES
+from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
 from llama_stack.providers.remote.post_training.nvidia import NvidiaPostTrainingConfig
-from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
 
 
 def get_distribution_template() -> DistributionTemplate:
     providers = {
         "inference": ["remote::nvidia"],
         "vector_io": ["inline::faiss"],
-        "safety": ["inline::llama-guard"],
+        "safety": ["remote::nvidia"],
         "post_training": ["remote::nvidia"],
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "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",
-        ],
+        "datasetio": ["inline::localfs"],
+        "scoring": ["inline::basic"],
+        "tool_runtime": ["inline::rag-runtime"],
     }
 
     inference_provider = Provider(
@@ -45,55 +39,61 @@ def get_distribution_template() -> DistributionTemplate:
         provider_type="remote::nvidia",
         config=NvidiaPostTrainingConfig.sample_run_config(),
     )
+    safety_provider = Provider(
+        provider_id="nvidia",
+        provider_type="remote::nvidia",
+        config=NVIDIASafetyConfig.sample_run_config(),
+    )
+    inference_model = ModelInput(
+        model_id="${env.INFERENCE_MODEL}",
+        provider_id="nvidia",
+    )
+    safety_model = ModelInput(
+        model_id="${env.SAFETY_MODEL}",
+        provider_id="nvidia",
+    )
 
-    core_model_to_hf_repo = {m.descriptor(): m.huggingface_repo for m in all_registered_models()}
-    default_models = [
-        ModelInput(
-            model_id=core_model_to_hf_repo[m.llama_model] if m.llama_model else m.provider_model_id,
-            provider_model_id=m.provider_model_id,
-            provider_id="nvidia",
-            model_type=m.model_type,
-            metadata=m.metadata,
-        )
-        for m in _MODEL_ENTRIES
-    ]
+    available_models = {
+        "nvidia": MODEL_ENTRIES,
+    }
     default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::websearch",
-            provider_id="tavily-search",
-        ),
         ToolGroupInput(
             toolgroup_id="builtin::rag",
             provider_id="rag-runtime",
         ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
     ]
 
+    default_models = get_model_registry(available_models)
     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,
-        default_models=default_models,
+        available_models_by_provider=available_models,
         run_configs={
             "run.yaml": RunConfigSettings(
                 provider_overrides={
                     "inference": [inference_provider],
+                    "post_training": [post_training_provider],
                 },
                 default_models=default_models,
                 default_tool_groups=default_tool_groups,
             ),
+            "run-with-safety.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [
+                        inference_provider,
+                        safety_provider,
+                    ]
+                },
+                default_models=[inference_model, safety_model],
+                default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
+                default_tool_groups=default_tool_groups,
+            ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
-                "5001",
-                "Port for the Llama Stack distribution server",
-            ),
             "NVIDIA_API_KEY": (
                 "",
                 "NVIDIA API Key",
@@ -123,5 +123,17 @@ def get_distribution_template() -> DistributionTemplate:
                 "test-example-model@v1",
                 "NVIDIA Output Model Directory",
             ),
+            "GUARDRAILS_SERVICE_URL": (
+                "http://0.0.0.0:7331",
+                "URL for the NeMo Guardrails Service",
+            ),
+            "INFERENCE_MODEL": (
+                "Llama3.1-8B-Instruct",
+                "Inference model",
+            ),
+            "SAFETY_MODEL": (
+                "meta/llama-3.1-8b-instruct",
+                "Name of the model to use for safety",
+            ),
         },
     )

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

@@ -0,0 +1,110 @@
+version: '2'
+image_name: nvidia
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- post_training
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
+      api_key: ${env.NVIDIA_API_KEY:}
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
+      config_id: self-check
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
+  safety:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
+      config_id: self-check
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
+  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
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  tool_runtime:
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
+models:
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: nvidia
+  model_type: llm
+- metadata: {}
+  model_id: ${env.SAFETY_MODEL}
+  provider_id: nvidia
+  model_type: llm
+shields:
+- shield_id: ${env.SAFETY_MODEL}
+  provider_id: nvidia
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+server:
+  port: 8321

llama_stack/templates/nvidia/run.yaml

@@ -5,10 +5,10 @@ apis:
 - datasetio
 - eval
 - inference
+- post_training
 - safety
 - scoring
 - telemetry
-- post_training
 - tool_runtime
 - vector_io
 providers:
@@ -27,9 +27,19 @@ 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
-    config: {}
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
+      config_id: self-check
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
   agents:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
@@ -48,108 +58,148 @@ providers:
   eval:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
-    config: {}
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
   datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config: {}
   - provider_id: localfs
     provider_type: inline::localfs
-    config: {}
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
   scoring:
   - 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:}
-  post_training:
-  - provider_id: nvidia-customizer
-    provider_type: remote::nvidia
-    config:
-      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:}
-      user_id: ${env.NVIDIA_USER_ID:}
-      project_id: ${env.NVIDIA_PROJECT_ID:}
-      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:}
   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
 models:
+- metadata: {}
+  model_id: meta/llama3-8b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama3-8b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3-8B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama3-8b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama3-70b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama3-70b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3-70B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama3-70b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.1-8b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.1-8b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-8B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.1-8b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.1-70b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.1-70b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-70B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.1-70b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.1-405b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.1-405b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
   provider_id: nvidia
   provider_model_id: meta/llama-3.1-405b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.2-1b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.2-1b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-1B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.2-1b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.2-3b-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.2-3b-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-3B-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.2-3b-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.2-11b-vision-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.2-11b-vision-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.2-11b-vision-instruct
   model_type: llm
+- metadata: {}
+  model_id: meta/llama-3.2-90b-vision-instruct
+  provider_id: nvidia
+  provider_model_id: meta/llama-3.2-90b-vision-instruct
+  model_type: llm
 - metadata: {}
   model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
   provider_id: nvidia
   provider_model_id: meta/llama-3.2-90b-vision-instruct
   model_type: llm
 - metadata:
-    embedding_dimension: 1024
+    embedding_dimension: 2048
     context_length: 8192
-  model_id: baai/bge-m3
+  model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
   provider_id: nvidia
-  provider_model_id: baai/bge-m3
+  provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
+  model_type: embedding
+- metadata:
+    embedding_dimension: 1024
+    context_length: 512
+  model_id: nvidia/nv-embedqa-e5-v5
+  provider_id: nvidia
+  provider_model_id: nvidia/nv-embedqa-e5-v5
+  model_type: embedding
+- metadata:
+    embedding_dimension: 4096
+    context_length: 512
+  model_id: nvidia/nv-embedqa-mistral-7b-v2
+  provider_id: nvidia
+  provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
+  model_type: embedding
+- metadata:
+    embedding_dimension: 1024
+    context_length: 512
+  model_id: snowflake/arctic-embed-l
+  provider_id: nvidia
+  provider_model_id: snowflake/arctic-embed-l
   model_type: embedding
 shields: []
 vector_dbs: []
@@ -157,11 +207,7 @@ 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