Move tool_runtime.memory -> tool_runtime.rag

llama_stack/providers/inline/tool_runtime/rag/__init__.py

@@ -8,11 +8,11 @@ from typing import Any, Dict
 
 from llama_stack.providers.datatypes import Api
 
-from .config import MemoryToolRuntimeConfig
+from .config import RagToolRuntimeConfig
 from .memory import MemoryToolRuntimeImpl
 
 
-async def get_provider_impl(config: MemoryToolRuntimeConfig, deps: Dict[str, Any]):
+async def get_provider_impl(config: RagToolRuntimeConfig, deps: Dict[str, Any]):
     impl = MemoryToolRuntimeImpl(config, deps[Api.vector_io], deps[Api.inference])
     await impl.initialize()
     return impl

llama_stack/providers/inline/tool_runtime/rag/config.py

@@ -7,5 +7,5 @@
 from pydantic import BaseModel
 
 
-class MemoryToolRuntimeConfig(BaseModel):
+class RagToolRuntimeConfig(BaseModel):
     pass

llama_stack/providers/inline/tool_runtime/rag/memory.py

@@ -32,7 +32,7 @@ from llama_stack.providers.utils.memory.vector_store import (
     make_overlapped_chunks,
 )
 
-from .config import MemoryToolRuntimeConfig
+from .config import RagToolRuntimeConfig
 from .context_retriever import generate_rag_query
 
 log = logging.getLogger(__name__)
@@ -47,7 +47,7 @@ def make_random_string(length: int = 8):
 class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
     def __init__(
         self,
-        config: MemoryToolRuntimeConfig,
+        config: RagToolRuntimeConfig,
         vector_io_api: VectorIO,
         inference_api: Inference,
     ):

llama_stack/providers/registry/tool_runtime.py

@@ -21,8 +21,8 @@ def available_providers() -> List[ProviderSpec]:
             api=Api.tool_runtime,
             provider_type="inline::rag-runtime",
             pip_packages=[],
-            module="llama_stack.providers.inline.tool_runtime.memory",
-            config_class="llama_stack.providers.inline.tool_runtime.memory.config.MemoryToolRuntimeConfig",
+            module="llama_stack.providers.inline.tool_runtime.rag",
+            config_class="llama_stack.providers.inline.tool_runtime.rag.config.RagToolRuntimeConfig",
             api_dependencies=[Api.vector_io, Api.inference],
         ),
         InlineProviderSpec(