Restrict the changes to the new preprocessing API only.

llama_stack/templates/meta-reference-quantized-gpu/build.yaml

@@ -29,7 +29,4 @@ distribution_spec:
     - inline::code-interpreter
     - inline::rag-runtime
     - remote::model-context-protocol
-    preprocessing:
-    - inline::basic
-    - inline::simple_chunking
 image_type: conda

llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py

@@ -7,7 +7,6 @@
 from pathlib import Path
 
 from llama_stack.apis.models.models import ModelType
-from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
 from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
 from llama_stack.providers.inline.inference.meta_reference import (
     MetaReferenceQuantizedInferenceConfig,
@@ -36,7 +35,6 @@ def get_distribution_template() -> DistributionTemplate:
             "inline::rag-runtime",
             "remote::model-context-protocol",
         ],
-        "preprocessing": ["inline::basic", "inline::simple_chunking"],
     }
     default_tool_groups = [
         ToolGroupInput(
@@ -52,16 +50,6 @@ 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",
-        ),
-    ]
     name = "meta-reference-quantized-gpu"
     inference_provider = Provider(
         provider_id="meta-reference-inference",
@@ -108,7 +96,6 @@ def get_distribution_template() -> DistributionTemplate:
                 },
                 default_models=[inference_model, embedding_model],
                 default_tool_groups=default_tool_groups,
-                default_preprocessors=default_preprocessors,
             ),
         },
         run_config_env_vars={

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -5,7 +5,6 @@ apis:
 - datasetio
 - eval
 - inference
-- preprocessing
 - safety
 - scoring
 - telemetry
@@ -106,13 +105,6 @@ 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/meta-reference-quantized-gpu}/registry.db
@@ -138,10 +130,6 @@ tool_groups:
   provider_id: rag-runtime
 - toolgroup_id: builtin::code_interpreter
   provider_id: code-interpreter
-preprocessors:
-- preprocessor_id: builtin::basic
-  provider_id: basic
-- preprocessor_id: builtin::chunking
-  provider_id: simple_chunking
+preprocessors: []
 server:
   port: 8321