[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

tests/client-sdk/agents/test_agents.py

@@ -292,7 +292,7 @@ def test_rag_agent(llama_stack_client, agent_config):
         embedding_model="all-MiniLM-L6-v2",
         embedding_dimension=384,
     )
-    llama_stack_client.tool_runtime.rag_tool.insert_documents(
+    llama_stack_client.tool_runtime.rag_tool.insert(
         documents=documents,
         vector_db_id=vector_db_id,
         chunk_size_in_tokens=512,
@@ -321,4 +321,4 @@ def test_rag_agent(llama_stack_client, agent_config):
         )
         logs = [str(log) for log in EventLogger().log(response) if log is not None]
         logs_str = "".join(logs)
-        assert "Tool:rag_tool.query_context" in logs_str
+        assert "Tool:query_from_memory" in logs_str

tests/client-sdk/tool_runtime/test_rag_tool.py

@@ -73,7 +73,7 @@ def test_vector_db_insert_inline_and_query(
     llama_stack_client, single_entry_vector_db_registry, sample_documents
 ):
     vector_db_id = single_entry_vector_db_registry[0]
-    llama_stack_client.tool_runtime.rag_tool.insert_documents(
+    llama_stack_client.tool_runtime.rag_tool.insert(
         documents=sample_documents,
         chunk_size_in_tokens=512,
         vector_db_id=vector_db_id,
@@ -157,7 +157,7 @@ def test_vector_db_insert_from_url_and_query(
         for i, url in enumerate(urls)
     ]
 
-    llama_stack_client.tool_runtime.rag_tool.insert_documents(
+    llama_stack_client.tool_runtime.rag_tool.insert(
         documents=documents,
         vector_db_id=vector_db_id,
         chunk_size_in_tokens=512,