feat(api): add file_processing to Api enumeration and include FileProcessors in LlamaStack

This commit introduces a new enumeration value, `file_processing`, to the `Api` class, enhancing the API's capabilities for file management. Additionally, the `FileProcessors` class is now included in the `LlamaStack` class, allowing for better integration of file processing functionalities within the stack.

No functional changes were made to existing features.

src/llama_stack/apis/datatypes.py

@@ -82,6 +82,7 @@ class DynamicApiMeta(EnumMeta):
 @json_schema_type
 class Api(Enum, metaclass=DynamicApiMeta):
     """Enumeration of all available APIs in the Llama Stack system.
+    :cvar file_processing: File processing and management
     :cvar providers: Provider management and configuration
     :cvar inference: Text generation, chat completions, and embeddings
     :cvar safety: Content moderation and safety shields
@@ -104,7 +105,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
     :cvar prompts: Prompt versions and management
     :cvar inspect: Built-in system inspection and introspection
     """
-
+    file_processing = "file_processing"
     providers = "providers"
     inference = "inference"
     safety = "safety"

src/llama_stack/apis/file_processors/file_processors.py

@@ -0,0 +1,50 @@
+# 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, Protocol, runtime_checkable
+
+from pydantic import BaseModel, Field
+
+from llama_stack.apis.version import LLAMA_STACK_API_V1
+from llama_stack.core.telemetry.trace_protocol import trace_protocol
+from llama_stack.schema_utils import json_schema_type, webmethod
+
+
+@json_schema_type
+class ProcessedContent(BaseModel):
+    """
+    Result of file processing containing extracted content and metadata.
+    
+    :param content: Extracted text content from the file
+    :param metadata: Processing metadata including processor info, timing, etc.
+    """
+    content: str = Field(..., description="Extracted text content from file")
+    metadata: dict[str, Any] = Field(default_factory=dict, description="Processing metadata")
+
+
+@runtime_checkable
+@trace_protocol
+class FileProcessors(Protocol):
+    """File Processors
+    
+    This API provides document processing capabilities for extracting text content
+    from various file formats including PDFs, Word documents, and more.
+    """
+
+    @webmethod(route="/file-processors/process", method="POST", level=LLAMA_STACK_API_V1)
+    async def process_file(
+        self, 
+        file_data: bytes, 
+        filename: str,
+        options: dict[str, Any] | None = None
+    ) -> ProcessedContent:
+        """Process a file and return extracted text content.
+        
+        :param file_data: The raw file data as bytes
+        :param filename: Name of the file (used for format detection)
+        :param options: Optional processing options (processor-specific)
+        :returns: ProcessedContent with extracted text and metadata
+        """

src/llama_stack/core/stack.py

@@ -55,6 +55,7 @@ from llama_stack.core.store.registry import create_dist_registry
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.log import get_logger
 from llama_stack.providers.datatypes import Api
+from llama_stack.apis.file_processors import FileProcessors
 
 logger = get_logger(name=__name__, category="core")
 
@@ -82,6 +83,7 @@ class LlamaStack(
     Files,
     Prompts,
     Conversations,
+    FileProcessors,
 ):
     pass