perf: Optimize vector viz search performance

- Replace sequential Qdrant scroll calls with batch retrieve
  (50 HTTP requests → 1 request, ~50x faster vector fetch)

- Add point_id to SearchResult to enable batch retrieval by Qdrant point ID

- Reuse query embedding from search algorithm in viz_routes
  (eliminates redundant embedding call, saves ~30ms)

- Make BM25 encode() async with thread pool to avoid blocking event loop
  (~4.4s was blocking, now properly async)

- Run PCA computation in thread pool to avoid blocking event loop
  (~1.2s was blocking, now properly async)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

nextcloud_mcp_server/search/algorithms.py

@@ -140,6 +140,7 @@ class SearchResult:
         page_number: Page number for PDF documents (None for other doc types)
         chunk_index: Zero-based index of this chunk in the document
         total_chunks: Total number of chunks in the document
+        point_id: Qdrant point ID for batch vector retrieval (None if not from Qdrant)
     """
 
     id: int
@@ -153,6 +154,7 @@ class SearchResult:
     page_number: int | None = None
     chunk_index: int = 0
     total_chunks: int = 1
+    point_id: str | None = None
 
     def __post_init__(self):
         """Validate score is non-negative.
@@ -172,8 +174,15 @@ class SearchAlgorithm(ABC):
 
     All search algorithms must implement the search() method with consistent
     interface, allowing them to be used interchangeably.
+
+    Attributes:
+        query_embedding: The query embedding generated during the last search.
+            Available after search() completes for algorithms that use embeddings.
+            Can be reused by callers to avoid redundant embedding generation.
     """
 
+    query_embedding: list[float] | None = None
+
     @abstractmethod
     async def search(
         self,

nextcloud_mcp_server/search/bm25_hybrid.py

@@ -101,11 +101,13 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
         # Generate dense embedding for semantic search
         embedding_service = get_embedding_service()
         dense_embedding = await embedding_service.embed(query)
+        # Store for reuse by callers (e.g., viz_routes PCA visualization)
+        self.query_embedding = dense_embedding
         logger.debug(f"Generated dense embedding (dimension={len(dense_embedding)})")
 
         # Generate sparse embedding for BM25 keyword search
         bm25_service = get_bm25_service()
-        sparse_embedding = bm25_service.encode(query)
+        sparse_embedding = await bm25_service.encode_async(query)
         logger.debug(
             f"Generated sparse embedding "
             f"({len(sparse_embedding['indices'])} non-zero terms)"
@@ -218,6 +220,7 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
                     page_number=result.payload.get("page_number"),
                     chunk_index=result.payload.get("chunk_index", 0),
                     total_chunks=result.payload.get("total_chunks", 1),
+                    point_id=str(result.id),  # Qdrant point ID for batch retrieval
                 )
             )
 

nextcloud_mcp_server/search/semantic.py

@@ -78,6 +78,8 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
         # Generate embedding for query
         embedding_service = get_embedding_service()
         query_embedding = await embedding_service.embed(query)
+        # Store for reuse by callers (e.g., viz_routes PCA visualization)
+        self.query_embedding = query_embedding
         logger.debug(
             f"Generated embedding for query (dimension={len(query_embedding)})"
         )
@@ -164,6 +166,7 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
                     page_number=result.payload.get("page_number"),
                     chunk_index=result.payload.get("chunk_index", 0),
                     total_chunks=result.payload.get("total_chunks", 1),
+                    point_id=str(result.id),  # Qdrant point ID for batch retrieval
                 )
             )