benchmarks: fix and extend HNSW+DiskANN recompute vs no-recompute; docs: add fresh numbers and DiskANN notes

packages/leann-backend-diskann/leann_backend_diskann/diskann_backend.py

@@ -442,8 +442,14 @@ class DiskannSearcher(BaseSearcher):
             use_global_pruning = True
 
         # Perform search with suppressed C++ output based on log level
-        use_deferred_fetch = kwargs.get("USE_DEFERRED_FETCH", True)
+        # Strategy:
+        # - Traversal always uses PQ distances
+        # - If recompute_embeddings=True, do a single final rerank via deferred fetch
+        #   (fetch embeddings for the final candidate set only)
+        # - Do not recompute neighbor distances along the path
+        use_deferred_fetch = True if recompute_embeddings else False
         recompute_neighors = False
+
         with suppress_cpp_output_if_needed():
             labels, distances = self._index.batch_search(
                 query,

packages/leann-core/src/leann/chat.py

@@ -422,7 +422,6 @@ class LLMInterface(ABC):
                 top_k=10,
                 complexity=64,
                 beam_width=8,
-                USE_DEFERRED_FETCH=True,
                 skip_search_reorder=True,
                 recompute_beighbor_embeddings=True,
                 dedup_node_dis=True,
@@ -434,7 +433,6 @@ class LLMInterface(ABC):
         Supported kwargs:
             - complexity (int): Search complexity parameter (default: 32)
             - beam_width (int): Beam width for search (default: 4)
-            - USE_DEFERRED_FETCH (bool): Enable deferred fetch mode (default: False)
             - skip_search_reorder (bool): Skip search reorder step (default: False)
             - recompute_beighbor_embeddings (bool): Enable ZMQ embedding server for neighbor recomputation (default: False)
             - dedup_node_dis (bool): Deduplicate nodes by distance (default: False)