[memory refactor][6/n] Update naming and routes (#839)

Making a few small naming changes as per feedback:

- RAGToolRuntime methods are called `insert` and `query` to keep them
more general
- The tool names are changed to non-namespaced forms
`insert_into_memory` and `query_from_memory`
- The REST endpoints are more REST-ful

llama_stack/providers/inline/agents/meta_reference/agent_instance.py

@@ -84,7 +84,7 @@ def make_random_string(length: int = 8):
 
 
 TOOLS_ATTACHMENT_KEY_REGEX = re.compile(r"__tools_attachment__=(\{.*?\})")
-MEMORY_QUERY_TOOL = "rag_tool.query_context"
+MEMORY_QUERY_TOOL = "query_from_memory"
 WEB_SEARCH_TOOL = "web_search"
 MEMORY_GROUP = "builtin::memory"
 
@@ -432,16 +432,16 @@ class ChatAgent(ShieldRunnerMixin):
                         )
                     )
                 )
-                result = await self.tool_runtime_api.rag_tool.query_context(
+                result = await self.tool_runtime_api.rag_tool.query(
                     content=concat_interleaved_content(
                         [msg.content for msg in input_messages]
                     ),
+                    vector_db_ids=vector_db_ids,
                     query_config=RAGQueryConfig(
                         query_generator_config=DefaultRAGQueryGeneratorConfig(),
                         max_tokens_in_context=4096,
                         max_chunks=5,
                     ),
-                    vector_db_ids=vector_db_ids,
                 )
                 retrieved_context = result.content
 
@@ -882,7 +882,7 @@ class ChatAgent(ShieldRunnerMixin):
             )
             for a in data
         ]
-        await self.tool_runtime_api.rag_tool.insert_documents(
+        await self.tool_runtime_api.rag_tool.insert(
             documents=documents,
             vector_db_id=vector_db_id,
             chunk_size_in_tokens=512,

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

@@ -61,7 +61,7 @@ class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
     async def shutdown(self):
         pass
 
-    async def insert_documents(
+    async def insert(
         self,
         documents: List[RAGDocument],
         vector_db_id: str,
@@ -87,15 +87,16 @@ class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
             vector_db_id=vector_db_id,
         )
 
-    async def query_context(
+    async def query(
         self,
         content: InterleavedContent,
-        query_config: RAGQueryConfig,
         vector_db_ids: List[str],
+        query_config: Optional[RAGQueryConfig] = None,
     ) -> RAGQueryResult:
         if not vector_db_ids:
             return RAGQueryResult(content=None)
 
+        query_config = query_config or RAGQueryConfig()
         query = await generate_rag_query(
             query_config.query_generator_config,
             content,
@@ -159,11 +160,11 @@ class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
         # encountering fatals.
         return [
             ToolDef(
-                name="rag_tool.query_context",
+                name="query_from_memory",
                 description="Retrieve context from memory",
             ),
             ToolDef(
-                name="rag_tool.insert_documents",
+                name="insert_into_memory",
                 description="Insert documents into memory",
             ),
         ]