Reverted the change in handling the case of no chunks found.

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

@@ -129,7 +129,7 @@ class MemoryToolRuntimeImpl(ToolsProtocolPrivate, ToolRuntime, RAGToolRuntime):
         scores = [s for r in results for s in r.scores]
 
         if not chunks:
-            raise ValueError("The knowledge search tool did not find any information relevant to the query.")
+            return RAGQueryResult(content=None)
 
         # sort by score
         chunks, scores = zip(*sorted(zip(chunks, scores, strict=False), key=lambda x: x[1], reverse=True), strict=False)  # type: ignore

tests/unit/rag/test_rag_query.py

@@ -4,11 +4,10 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from unittest.mock import AsyncMock, MagicMock
+from unittest.mock import MagicMock
 
 import pytest
 
-from llama_stack.apis.vector_io import QueryChunksResponse
 from llama_stack.providers.inline.tool_runtime.rag.memory import MemoryToolRuntimeImpl
 
 
@@ -18,16 +17,3 @@ class TestRagQuery:
         rag_tool = MemoryToolRuntimeImpl(config=MagicMock(), vector_io_api=MagicMock(), inference_api=MagicMock())
         with pytest.raises(ValueError):
             await rag_tool.query(content=MagicMock(), vector_db_ids=[])
-
-    @pytest.mark.asyncio
-    async def test_query_raises_on_no_chunks_found(self):
-        vector_io_api = MagicMock()
-        vector_io_api.query_chunks = AsyncMock(return_value=QueryChunksResponse(chunks=[], scores=[]))
-
-        rag_tool = MemoryToolRuntimeImpl(
-            config=MagicMock(),
-            vector_io_api=vector_io_api,
-            inference_api=MagicMock(),
-        )
-        with pytest.raises(ValueError):
-            await rag_tool.query(content=MagicMock(), vector_db_ids=["test_db"])