LCORE-1426: remove redundant max_chunks param and rename _fetch_solr_rag to _fetch_okp_rag

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: are-ces

src/utils/vector_search.py

@@ -443,7 +443,6 @@ async def _fetch_byok_rag(  # pylint: disable=too-many-locals
     client: AsyncLlamaStackClient,
     query: str,
     vector_store_ids: Optional[list[str]] = None,
-    max_chunks: Optional[int] = None,
 ) -> tuple[list[RAGChunk], list[ReferencedDocument]]:
     """Fetch chunks and documents from BYOK RAG sources.
 
@@ -453,15 +452,13 @@ async def _fetch_byok_rag(  # pylint: disable=too-many-locals
         vector_store_ids: Optional list of vector store IDs to query.
             If provided, only these stores will be queried. If None, all stores
             (excluding Solr) will be queried.
-        max_chunks: Maximum number of chunks to return. If None, uses
-            rag.byok.max_chunks from configuration.
 
     Returns:
         Tuple containing:
         - rag_chunks: RAG chunks from BYOK RAG
         - referenced_documents: Documents referenced in BYOK RAG results
     """
-    limit = max_chunks if max_chunks is not None else configuration.rag.byok.max_chunks
+    limit = configuration.rag.byok.max_chunks
     rag_chunks: list[RAGChunk] = []
     referenced_documents: list[ReferencedDocument] = []
 
@@ -550,7 +547,7 @@ async def _fetch_byok_rag(  # pylint: disable=too-many-locals
     return rag_chunks, referenced_documents
 
 
-async def _fetch_solr_rag(  # pylint: disable=too-many-locals
+async def _fetch_okp_rag(  # pylint: disable=too-many-locals
     client: AsyncLlamaStackClient,
     query: str,
     solr: Optional[SolrVectorSearchRequest] = None,
@@ -561,8 +558,6 @@ async def _fetch_solr_rag(  # pylint: disable=too-many-locals
         client: The AsyncLlamaStackClient to use for the request
         query: The user's query
         solr: Structured Solr inline RAG request from the API (optional).
-        max_chunks: Maximum number of chunks to return. If None, uses
-            rag.okp.max_chunks from configuration.
 
     Returns:
         Tuple containing:
@@ -658,10 +653,8 @@ async def build_rag_context(  # pylint: disable=too-many-locals,too-many-branche
     top_k = configuration.rag.retrieval.inline.max_chunks
 
     # Fetch from each source using per-source limits for the reranking pool
-    byok_chunks_task = _fetch_byok_rag(
-        client, query, vector_store_ids, max_chunks=configuration.rag.byok.max_chunks
-    )
-    solr_chunks_task = _fetch_solr_rag(client, query, solr)
+    byok_chunks_task = _fetch_byok_rag(client, query, vector_store_ids)
+    solr_chunks_task = _fetch_okp_rag(client, query, solr)
 
     (byok_chunks, byok_documents), (solr_chunks, solr_documents) = await asyncio.gather(
         byok_chunks_task, solr_chunks_task

tests/unit/utils/test_vector_search.py

@@ -22,7 +22,7 @@
     _extract_byok_rag_chunks,
     _extract_solr_document_metadata,
     _fetch_byok_rag,
-    _fetch_solr_rag,
+    _fetch_okp_rag,
     _format_rag_context,
     _get_okp_base_url,
     _get_solr_vector_store_ids,
@@ -703,7 +703,7 @@ async def test_request_id_not_in_inline_config_skips_byok(
 
 
 class TestFetchSolrRag:
-    """Tests for _fetch_solr_rag async function."""
+    """Tests for _fetch_okp_rag async function."""
 
     @pytest.mark.asyncio
     async def test_solr_disabled(self, mocker: MockerFixture) -> None:
@@ -713,7 +713,7 @@ async def test_solr_disabled(self, mocker: MockerFixture) -> None:
         mocker.patch("utils.vector_search.configuration", config_mock)
 
         client_mock = mocker.AsyncMock()
-        rag_chunks, referenced_docs = await _fetch_solr_rag(client_mock, "test query")
+        rag_chunks, referenced_docs = await _fetch_okp_rag(client_mock, "test query")
 
         assert rag_chunks == []
         assert referenced_docs == []
@@ -745,7 +745,7 @@ async def test_solr_enabled_success(self, mocker: MockerFixture) -> None:
         client_mock = mocker.AsyncMock()
         client_mock.vector_io.query.return_value = query_response
 
-        rag_chunks, _referenced_docs = await _fetch_solr_rag(client_mock, "test query")
+        rag_chunks, _referenced_docs = await _fetch_okp_rag(client_mock, "test query")
 
         assert len(rag_chunks) > 0
         assert rag_chunks[0].content == "Solr content"
@@ -775,7 +775,7 @@ async def test_solr_enabled_passes_request_mode_to_vector_io(
         client_mock = mocker.AsyncMock()
         client_mock.vector_io.query.return_value = query_response
 
-        await _fetch_solr_rag(
+        await _fetch_okp_rag(
             client_mock,
             "test query",
             SolrVectorSearchRequest(mode="semantic", filters={"fq": ["x:y"]}),