fix: address first round of reviews

Signed-off-by: Alina Ryan <aliryan@redhat.com>

src/llama_stack/core/resolver.py

@@ -34,7 +34,7 @@ from llama_stack_api import (
     DatasetsProtocolPrivate,
     Eval,
     ExternalApiSpec,
-    FileProcessor,
+    FileProcessors,
     Files,
     Inference,
     InferenceProvider,
@@ -101,7 +101,7 @@ def api_protocol_map(external_apis: dict[Api, ExternalApiSpec] | None = None) ->
         Api.files: Files,
         Api.prompts: Prompts,
         Api.conversations: Conversations,
-        Api.file_processor: FileProcessor,
+        Api.file_processors: FileProcessors,
     }
 
     if external_apis:

src/llama_stack/distributions/ci-tests/build.yaml

@@ -29,8 +29,6 @@ distribution_spec:
     - provider_type: remote::weaviate
     files:
     - provider_type: inline::localfs
-    file_processor:
-    - provider_type: inline::reference
     safety:
     - provider_type: inline::llama-guard
     - provider_type: inline::code-scanner

src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/ci-tests/run.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/starter-gpu/build.yaml

@@ -30,8 +30,6 @@ distribution_spec:
     - provider_type: remote::weaviate
     files:
     - provider_type: inline::localfs
-    file_processor:
-    - provider_type: inline::reference
     safety:
     - provider_type: inline::llama-guard
     - provider_type: inline::code-scanner

src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/starter-gpu/run.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/starter/build.yaml

@@ -30,8 +30,6 @@ distribution_spec:
     - provider_type: remote::weaviate
     files:
     - provider_type: inline::localfs
-    file_processor:
-    - provider_type: inline::reference
     safety:
     - provider_type: inline::llama-guard
     - provider_type: inline::code-scanner

src/llama_stack/distributions/starter/run-with-postgres-store.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/starter/run.yaml

@@ -5,7 +5,6 @@ apis:
 - batches
 - datasetio
 - eval
-- file_processor
 - files
 - inference
 - post_training
@@ -154,9 +153,6 @@ providers:
       metadata_store:
         table_name: files_metadata
         backend: sql_default
-  file_processor:
-  - provider_id: reference
-    provider_type: inline::reference
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard

src/llama_stack/distributions/starter/starter.py

@@ -123,7 +123,6 @@ def get_distribution_template(name: str = "starter") -> DistributionTemplate:
             BuildProvider(provider_type="remote::weaviate"),
         ],
         "files": [BuildProvider(provider_type="inline::localfs")],
-        "file_processor": [BuildProvider(provider_type="inline::reference")],
         "safety": [
             BuildProvider(provider_type="inline::llama-guard"),
             BuildProvider(provider_type="inline::code-scanner"),

src/llama_stack/log.py

@@ -45,7 +45,7 @@ CATEGORIES = [
     "providers",
     "models",
     "files",
-    "file_processor",
+    "file_processors",
     "vector_io",
     "tool_runtime",
     "cli",

src/llama_stack/providers/inline/file_processor/reference/__init__.py

@@ -1,15 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from .config import ReferenceFileProcessorImplConfig
-
-
-async def get_provider_impl(config: ReferenceFileProcessorImplConfig, deps):
-    from .reference import ReferenceFileProcessorImpl
-
-    impl = ReferenceFileProcessorImpl(config, deps)
-    await impl.initialize()
-    return impl

src/llama_stack/providers/inline/file_processor/reference/config.py

@@ -1,15 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from pydantic import BaseModel
-
-
-class ReferenceFileProcessorImplConfig(BaseModel):
-    """Configuration for the reference file processor implementation."""
-
-    @staticmethod
-    def sample_run_config(**kwargs):
-        return {}

src/llama_stack/providers/inline/file_processor/reference/reference.py

@@ -1,41 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from typing import Any
-
-from llama_stack_api import FileProcessor, ProcessedContent, VectorStoreChunkingStrategy
-
-from .config import ReferenceFileProcessorImplConfig
-
-
-class ReferenceFileProcessorImpl(FileProcessor):
-    """Reference implementation of the FileProcessor API."""
-
-    def __init__(self, config: ReferenceFileProcessorImplConfig, deps: dict[str, Any]):
-        self.config = config
-        self.deps = deps
-
-    async def initialize(self) -> None:
-        pass
-
-    async def process_file(
-        self,
-        file_data: bytes,
-        filename: str,
-        options: dict[str, Any] | None = None,
-        chunking_strategy: VectorStoreChunkingStrategy | None = None,
-        include_embeddings: bool = False,
-    ) -> ProcessedContent:
-        """Process a file into structured content."""
-        return ProcessedContent(
-            content="Placeholder content",
-            chunks=None,
-            embeddings=None,
-            metadata={
-                "processor": "reference",
-                "filename": filename,
-            },
-        )

src/llama_stack/providers/registry/file_processor.py

@@ -1,20 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from llama_stack_api import Api, InlineProviderSpec, ProviderSpec
-
-
-def available_providers() -> list[ProviderSpec]:
-    return [
-        InlineProviderSpec(
-            api=Api.file_processor,
-            provider_type="inline::reference",
-            pip_packages=[],
-            module="llama_stack.providers.inline.file_processor.reference",
-            config_class="llama_stack.providers.inline.file_processor.reference.config.ReferenceFileProcessorImplConfig",
-            description="Reference file processor implementation (placeholder for development)",
-        ),
-    ]

src/llama_stack/providers/registry/file_processors.py

@@ -0,0 +1,11 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from llama_stack_api import ProviderSpec
+
+
+def available_providers() -> list[ProviderSpec]:
+    return []

src/llama_stack_api/__init__.py

@@ -112,7 +112,7 @@ from .datatypes import (
     VectorStoresProtocolPrivate,
 )
 from .eval import BenchmarkConfig, Eval, EvalCandidate, EvaluateResponse, ModelCandidate
-from .file_processor import FileProcessor, ProcessedContent, ProcessFileRequest
+from .file_processors import FileProcessors, ProcessedContent, ProcessFileRequest
 from .files import (
     ExpiresAfter,
     Files,
@@ -519,7 +519,7 @@ __all__ = [
     "ExpiresAfter",
     "ExternalApiSpec",
     "ExtraBodyField",
-    "FileProcessor",
+    "FileProcessors",
     "Files",
     "Fp8QuantizationConfig",
     "clear_dynamic_schema_types",

src/llama_stack_api/datatypes.py

@@ -110,7 +110,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
     :cvar benchmarks: Benchmark suite management
     :cvar tool_groups: Tool group organization
     :cvar files: File storage and management
-    :cvar file_processor: File parsing and processing operations
+    :cvar file_processors: File parsing and processing operations
     :cvar prompts: Prompt versions and management
     :cvar inspect: Built-in system inspection and introspection
     """
@@ -135,7 +135,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
     benchmarks = "benchmarks"
     tool_groups = "tool_groups"
     files = "files"
-    file_processor = "file_processor"
+    file_processors = "file_processors"
     prompts = "prompts"
     conversations = "conversations"
 

src/llama_stack_api/file_processors.py

@@ -53,7 +53,7 @@ class ProcessedContent(BaseModel):
 
 @telemetry_traceable
 @runtime_checkable
-class FileProcessor(Protocol):
+class FileProcessors(Protocol):
     """
     File Processor API for converting files into structured, processable content.
 
@@ -72,7 +72,7 @@ class FileProcessor(Protocol):
     processing capabilities, and optimization strategies.
     """
 
-    @webmethod(route="/file-processor/process", method="POST", level=LLAMA_STACK_API_V1ALPHA)
+    @webmethod(route="/file-processors/process", method="POST", level=LLAMA_STACK_API_V1ALPHA)
     async def process_file(
         self,
         file_data: bytes,