Updated the configuration templates to include the builtin preprocessors.

llama_stack/templates/nvidia/build.yaml

@@ -27,4 +27,7 @@ distribution_spec:
     - inline::code-interpreter
     - inline::rag-runtime
     - remote::model-context-protocol
+    preprocessing:
+    - inline::basic
+    - inline::simple_chunking
 image_type: conda

llama_stack/templates/nvidia/nvidia.py

@@ -6,6 +6,7 @@
 
 from pathlib import Path
 
+from llama_stack.apis.preprocessing.preprocessors import PreprocessorInput
 from llama_stack.distribution.datatypes import Provider, ToolGroupInput
 from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
 from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
@@ -29,6 +30,7 @@ def get_distribution_template() -> DistributionTemplate:
             "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
+        "preprocessing": ["inline::basic", "inline::simple_chunking"],
     }
 
     inference_provider = Provider(
@@ -54,6 +56,16 @@ def get_distribution_template() -> DistributionTemplate:
             provider_id="code-interpreter",
         ),
     ]
+    default_preprocessors = [
+        PreprocessorInput(
+            preprocessor_id="builtin::basic",
+            provider_id="basic",
+        ),
+        PreprocessorInput(
+            preprocessor_id="builtin::chunking",
+            provider_id="simple_chunking",
+        ),
+    ]
 
     default_models = get_model_registry(available_models)
     return DistributionTemplate(
@@ -71,6 +83,7 @@ def get_distribution_template() -> DistributionTemplate:
                 },
                 default_models=default_models,
                 default_tool_groups=default_tool_groups,
+                default_preprocessors=default_preprocessors,
             ),
         },
         run_config_env_vars={

llama_stack/templates/nvidia/run.yaml

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- preprocessing
 - safety
 - scoring
 - telemetry
@@ -86,6 +87,13 @@ providers:
   - provider_id: model-context-protocol
     provider_type: remote::model-context-protocol
     config: {}
+  preprocessing:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  - provider_id: simple_chunking
+    provider_type: inline::simple_chunking
+    config: {}
 metadata_store:
   type: sqlite
   db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
@@ -220,6 +228,10 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
-preprocessors: []
+preprocessors:
+- preprocessor_id: builtin::basic
+  provider_id: basic
+- preprocessor_id: builtin::chunking
+  provider_id: simple_chunking
 server:
   port: 8321