Updated the configuration templates to include the builtin preprocessors.

llama_stack/templates/tgi/build.yaml

@@ -30,4 +30,7 @@ distribution_spec:
     - inline::code-interpreter
     - inline::rag-runtime
     - remote::model-context-protocol
+    preprocessing:
+    - inline::basic
+    - inline::simple_chunking
 image_type: conda

llama_stack/templates/tgi/run-with-safety.yaml

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- preprocessing
 - safety
 - scoring
 - telemetry
@@ -89,6 +90,13 @@ 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/tgi}/registry.db
@@ -114,6 +122,10 @@ 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

llama_stack/templates/tgi/run.yaml

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- preprocessing
 - safety
 - scoring
 - telemetry
@@ -88,6 +89,13 @@ 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/tgi}/registry.db
@@ -113,6 +121,10 @@ 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

llama_stack/templates/tgi/tgi.py

@@ -7,6 +7,7 @@
 from pathlib import Path
 
 from llama_stack.apis.models.models import ModelType
+from llama_stack.apis.preprocessing.preprocessors import PreprocessorInput
 from llama_stack.distribution.datatypes import (
     ModelInput,
     Provider,
@@ -38,6 +39,7 @@ def get_distribution_template() -> DistributionTemplate:
             "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
+        "preprocessing": ["inline::basic", "inline::simple_chunking"],
     }
     name = "tgi"
     inference_provider = Provider(
@@ -88,6 +90,16 @@ 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",
+        ),
+    ]
 
     return DistributionTemplate(
         name=name,
@@ -104,6 +116,7 @@ def get_distribution_template() -> DistributionTemplate:
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
+                default_preprocessors=default_preprocessors,
             ),
             "run-with-safety.yaml": RunConfigSettings(
                 provider_overrides={
@@ -125,6 +138,7 @@ def get_distribution_template() -> DistributionTemplate:
                 ],
                 default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
                 default_tool_groups=default_tool_groups,
+                default_preprocessors=default_preprocessors,
             ),
         },
         run_config_env_vars={