all templates to include toolgroups and tool runtime

llama_stack/templates/hf-endpoint/build.yaml

@@ -2,7 +2,6 @@ version: '2'
 name: hf-endpoint
 distribution_spec:
   description: Use (an external) Hugging Face Inference Endpoint for running LLM inference
-  docker_image: null
   providers:
     inference:
     - remote::hf::endpoint
@@ -25,4 +24,9 @@ distribution_spec:
     - inline::basic
     - inline::llm-as-judge
     - inline::braintrust
+    tool_runtime:
+    - remote::brave-search
+    - remote::tavily-search
+    - inline::code-interpreter
+    - inline::memory-runtime
 image_type: conda

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -5,7 +5,12 @@
 # the root directory of this source tree.
 
 from llama_stack.apis.models.models import ModelType
-from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
+from llama_stack.distribution.datatypes import (
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
 from llama_stack.providers.inline.inference.sentence_transformers import (
     SentenceTransformersInferenceConfig,
 )
@@ -24,6 +29,12 @@ def get_distribution_template() -> DistributionTemplate:
         "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::memory-runtime",
+        ],
     }
     name = "hf-endpoint"
     inference_provider = Provider(
@@ -58,6 +69,20 @@ def get_distribution_template() -> DistributionTemplate:
             "embedding_dimension": 384,
         },
     )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::memory",
+            provider_id="memory-runtime",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::code_interpreter",
+            provider_id="code-interpreter",
+        ),
+    ]
 
     return DistributionTemplate(
         name=name,
@@ -74,6 +99,7 @@ def get_distribution_template() -> DistributionTemplate:
                     "memory": [memory_provider],
                 },
                 default_models=[inference_model, embedding_model],
+                default_tool_groups=default_tool_groups,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
@@ -96,6 +122,7 @@ def get_distribution_template() -> DistributionTemplate:
                     embedding_model,
                 ],
                 default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
+                default_tool_groups=default_tool_groups,
             ),
         },
         run_config_env_vars={

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -1,6 +1,5 @@
 version: '2'
 image_name: hf-endpoint
-docker_image: null
 conda_env: hf-endpoint
 apis:
 - agents
@@ -11,6 +10,7 @@ apis:
 - safety
 - scoring
 - telemetry
+- tool_runtime
 providers:
   inference:
   - provider_id: hf-endpoint
@@ -75,33 +75,50 @@ providers:
     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/hf-endpoint}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: hf-endpoint
-  provider_model_id: null
   model_type: llm
 - metadata: {}
   model_id: ${env.SAFETY_MODEL}
   provider_id: hf-endpoint-safety
-  provider_model_id: null
   model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
-  provider_model_id: null
   model_type: embedding
 shields:
-- params: null
-  shield_id: ${env.SAFETY_MODEL}
-  provider_id: null
-  provider_shield_id: null
+- shield_id: ${env.SAFETY_MODEL}
 memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter

llama_stack/templates/hf-endpoint/run.yaml

@@ -1,6 +1,5 @@
 version: '2'
 image_name: hf-endpoint
-docker_image: null
 conda_env: hf-endpoint
 apis:
 - agents
@@ -11,6 +10,7 @@ apis:
 - safety
 - scoring
 - telemetry
+- tool_runtime
 providers:
   inference:
   - provider_id: hf-endpoint
@@ -70,24 +70,45 @@ providers:
     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/hf-endpoint}/registry.db
 models:
 - metadata: {}
   model_id: ${env.INFERENCE_MODEL}
   provider_id: hf-endpoint
-  provider_model_id: null
   model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2
   provider_id: sentence-transformers
-  provider_model_id: null
   model_type: embedding
 shields: []
 memory_banks: []
 datasets: []
 scoring_fns: []
 eval_tasks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::memory
+  provider_id: memory-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter