updated nvidia distro with recent apis

distributions/inline-nvidia/compose.yaml

@@ -1,6 +1,6 @@
 services:
   nim:
-    image: nvcr.io/nim/meta/llama-3.1-8b-instruct:latest
+    image: ${DOCKER_IMAGE:-nvcr.io/nim/meta/llama-3.1-8b-instruct:latest}
     network_mode: "host"
     volumes:
     - nim-llm-cache:/opt/nim/.cache
@@ -55,4 +55,4 @@ services:
         window: 60s
 volumes:
   nim-llm-cache:
-    driver: local
+    driver: local

distributions/inline-nvidia/run.yaml

@@ -1,20 +1,23 @@
 version: '2'
 image_name: nvidia
-docker_image: null
 conda_env: nvidia
 apis:
 - agents
+- datasetio
+- eval
 - inference
 - memory
 - safety
+- scoring
 - telemetry
+- tool_runtime
 providers:
   inference:
   - provider_id: nvidia
     provider_type: remote::nvidia
     config:
       url: http://localhost:8000
-      api_key: ${env.NVIDIA_API_KEY}
+      api_key: ${env.NVIDIA_API_KEY} # TODO: don't need api key, code adjustments needed
   memory:
   - provider_id: faiss
     provider_type: inline::faiss
@@ -38,19 +41,60 @@ providers:
   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: {}
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config: {}
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config: {}
+  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:}
+  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: memory-runtime
+    provider_type: inline::memory-runtime
     config: {}
 metadata_store:
-  namespace: null
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: nvidia
-  provider_model_id: null
+  model_type: llm
 shields: []
 memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
-
+tool_groups: []