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

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