From 2bd557d1cfd2fd1319f8d3294740571c79e3f780 Mon Sep 17 00:00:00 2001
From: Andy Lee <andylizf@outlook.com>
Date: Thu, 14 Aug 2025 11:08:34 -0700
Subject: [PATCH] hnsw: move pruned/no-recompute assertion into backend; api:
 drop global assertion; docs: will adjust after benchmarking

---
 README.md                                     |  1 +
 benchmarks/benchmark_no_recompute.py          | 82 +++++++++++++++++++
 .../leann_backend_hnsw/hnsw_backend.py        |  8 +-
 3 files changed, 88 insertions(+), 3 deletions(-)
 create mode 100644 benchmarks/benchmark_no_recompute.py

diff --git a/README.md b/README.md
index a158a38..b53fb51 100755
--- a/README.md
+++ b/README.md
@@ -515,6 +515,7 @@ Options:
   --top-k N                   Number of results (default: 5)
   --complexity N              Search complexity (default: 64)
   --recompute                 Use recomputation for highest accuracy
+  --no-recompute              Disable recomputation (requires non-compact HNSW index)
   --pruning-strategy {global,local,proportional}
 ```
 
diff --git a/benchmarks/benchmark_no_recompute.py b/benchmarks/benchmark_no_recompute.py
new file mode 100644
index 0000000..8f218d1
--- /dev/null
+++ b/benchmarks/benchmark_no_recompute.py
@@ -0,0 +1,82 @@
+import os
+import time
+from pathlib import Path
+
+from leann import LeannBuilder, LeannSearcher
+
+
+def ensure_index(
+    index_path: str, num_docs: int = 5000, is_recompute: bool = True, is_compact: bool = True
+):
+    path = Path(index_path)
+    if (path.parent / f"{path.stem}.meta.json").exists():
+        return
+
+    builder = LeannBuilder(
+        backend_name="hnsw",
+        embedding_model=os.getenv("LEANN_EMBED_MODEL", "facebook/contriever"),
+        embedding_mode=os.getenv("LEANN_EMBED_MODE", "sentence-transformers"),
+        graph_degree=32,
+        complexity=64,
+        is_compact=is_compact,
+        is_recompute=is_recompute,
+        num_threads=4,
+    )
+
+    for i in range(num_docs):
+        builder.add_text(
+            f"This is a test document number {i}. It contains some repeated text for benchmarking."
+        )
+
+    builder.build_index(index_path)
+
+
+def bench_once(index_path: str, recompute: bool, top_k: int = 10) -> float:
+    searcher = LeannSearcher(index_path=index_path)
+    t0 = time.time()
+    _ = searcher.search(
+        "test document number 42",
+        top_k=top_k,
+        complexity=64,
+        prune_ratio=0.0,
+        recompute_embeddings=recompute,
+    )
+    return time.time() - t0
+
+
+def main():
+    base = Path.cwd() / ".leann" / "indexes" / "bench"
+    base.parent.mkdir(parents=True, exist_ok=True)
+    index_path_recompute = str(base / "recompute.leann")
+    index_path_norecompute = str(base / "norecompute.leann")
+
+    # Build two variants: pruned (recompute) and non-compact (no-recompute)
+    ensure_index(index_path_recompute, is_recompute=True, is_compact=True)
+    ensure_index(index_path_norecompute, is_recompute=False, is_compact=False)
+
+    # Warm up
+    bench_once(index_path_recompute, recompute=True)
+    bench_once(index_path_norecompute, recompute=False)
+
+    t_recompute = bench_once(index_path_recompute, recompute=True)
+    t_norecompute = bench_once(index_path_norecompute, recompute=False)
+
+    size_recompute = sum(
+        f.stat().st_size for f in Path(index_path_recompute).parent.iterdir() if f.is_file()
+    )
+    size_norecompute = sum(
+        f.stat().st_size for f in Path(index_path_norecompute).parent.iterdir() if f.is_file()
+    )
+
+    print("Benchmark results (HNSW):")
+    print(
+        f"  recompute=True:  search_time={t_recompute:.3f}s, size={size_recompute / 1024 / 1024:.1f}MB"
+    )
+    print(
+        f"  recompute=False: search_time={t_norecompute:.3f}s, size={size_norecompute / 1024 / 1024:.1f}MB"
+    )
+    print("Expectation: no-recompute should be faster but larger on disk.")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py
index 8473630..2ec6e39 100644
--- a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py
+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py
@@ -185,9 +185,11 @@ class HNSWSearcher(BaseSearcher):
         """
         from . import faiss  # type: ignore
 
-        if not recompute_embeddings:
-            if self.is_pruned:
-                raise RuntimeError("Recompute is required for pruned index.")
+        if not recompute_embeddings and self.is_pruned:
+            raise RuntimeError(
+                "Recompute is required for pruned/compact HNSW index. "
+                "Re-run search with --recompute, or rebuild with --no-recompute and --no-compact."
+            )
         if recompute_embeddings:
             if zmq_port is None:
                 raise ValueError("zmq_port must be provided if recompute_embeddings is True")