chore(cleanup)!: remove tool_runtime.rag_tool

Kill the `builtin::rag` tool group completely since it is no longer
targeted. We use the Responses implementation for knowledge_search which
uses the `openai_vector_stores` pathway.

llama_stack/distributions/nvidia/build.yaml

@@ -19,8 +19,7 @@ distribution_spec:
     - provider_type: remote::nvidia
     scoring:
     - provider_type: inline::basic
-    tool_runtime:
-    - provider_type: inline::rag-runtime
+    tool_runtime: []
     files:
     - provider_type: inline::localfs
 image_type: venv

llama_stack/distributions/nvidia/nvidia.py

@@ -6,7 +6,7 @@
 
 from pathlib import Path
 
-from llama_stack.core.datatypes import BuildProvider, ModelInput, Provider, ShieldInput, ToolGroupInput
+from llama_stack.core.datatypes import BuildProvider, ModelInput, Provider, ShieldInput
 from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
 from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig
 from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
@@ -28,7 +28,7 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
             BuildProvider(provider_type="remote::nvidia"),
         ],
         "scoring": [BuildProvider(provider_type="inline::basic")],
-        "tool_runtime": [BuildProvider(provider_type="inline::rag-runtime")],
+        "tool_runtime": [],
         "files": [BuildProvider(provider_type="inline::localfs")],
     }
 
@@ -66,12 +66,7 @@ def get_distribution_template(name: str = "nvidia") -> DistributionTemplate:
         provider_id="nvidia",
     )
 
-    default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::rag",
-            provider_id="rag-runtime",
-        ),
-    ]
+    default_tool_groups = []
 
     return DistributionTemplate(
         name=name,

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

@@ -80,9 +80,7 @@ providers:
   scoring:
   - provider_id: basic
     provider_type: inline::basic
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
+  tool_runtime: []
   files:
   - provider_id: meta-reference-files
     provider_type: inline::localfs
@@ -128,9 +126,7 @@ registered_resources:
   datasets: []
   scoring_fns: []
   benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
+  tool_groups: []
 server:
   port: 8321
 telemetry:

llama_stack/distributions/nvidia/run.yaml

@@ -69,9 +69,7 @@ providers:
   scoring:
   - provider_id: basic
     provider_type: inline::basic
-  tool_runtime:
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
+  tool_runtime: []
   files:
   - provider_id: meta-reference-files
     provider_type: inline::localfs
@@ -107,9 +105,7 @@ registered_resources:
   datasets: []
   scoring_fns: []
   benchmarks: []
-  tool_groups:
-  - toolgroup_id: builtin::rag
-    provider_id: rag-runtime
+  tool_groups: []
 server:
   port: 8321
 telemetry: