Docs/Core: Low-Resource Setups, SkyPilot Option, and No-Recompute (#45)
* docs: add SkyPilot template and instructions for running embeddings/index build on cloud GPU * docs: add low-resource note in README; point to config guide; suggest OpenAI embeddings, SkyPilot remote build, and --no-recompute * docs: consolidate low-resource guidance into config guide; README points to it * cli: add --no-recompute and --no-recompute-embeddings flags; docs: clarify HNSW requires --no-compact when disabling recompute * docs: dedupe recomputation guidance; keep single Low-resource setups section * sky: expand leann-build.yaml with configurable params and flags (backend, recompute, compact, embedding options) * hnsw: auto-disable compact when --no-recompute is used; docs: expand SkyPilot with -e overrides and copy-back example * docs+sky: simplify SkyPilot flow (auto-build on launch, rsync copy-back); clarify HNSW auto non-compact when no-recompute * feat: auto compact for hnsw when recompute * reader: non-destructive portability (relative hints + fallback); fix comments; sky: refine yaml * cli: unify flags to --recompute/--no-recompute for build/search/ask; docs: update references * chore: remove * hnsw: move pruned/no-recompute assertion into backend; api: drop global assertion; docs: will adjust after benchmarking * cli: use argparse.BooleanOptionalAction for paired flags (--recompute/--compact) across build/search/ask * docs: a real example on recompute * benchmarks: fix and extend HNSW+DiskANN recompute vs no-recompute; docs: add fresh numbers and DiskANN notes * benchmarks: unify HNSW & DiskANN into one clean script; isolate groups, fixed ports, warm-up, param complexity * docs: diskann recompute * core: auto-cleanup for LeannSearcher/LeannChat (__enter__/__exit__/__del__); ensure server terminate/kill robustness; benchmarks: use searcher.cleanup(); docs: suggest uv run * fix: hang on warnings * docs: boolean flags * docs: leann help
This commit is contained in:
Andy Lee
148
benchmarks/benchmark_no_recompute.py
Normal file
148
benchmarks/benchmark_no_recompute.py
Normal file
@@ -0,0 +1,148 @@
|
||||
import argparse
|
||||
import os
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
from leann import LeannBuilder, LeannSearcher
|
||||
|
||||
|
||||
def _meta_exists(index_path: str) -> bool:
|
||||
p = Path(index_path)
|
||||
return (p.parent / f"{p.stem}.meta.json").exists()
|
||||
|
||||
|
||||
def ensure_index(index_path: str, backend_name: str, num_docs: int, is_recompute: bool) -> None:
|
||||
# if _meta_exists(index_path):
|
||||
# return
|
||||
kwargs = {}
|
||||
if backend_name == "hnsw":
|
||||
kwargs["is_compact"] = is_recompute
|
||||
builder = LeannBuilder(
|
||||
backend_name=backend_name,
|
||||
embedding_model=os.getenv("LEANN_EMBED_MODEL", "facebook/contriever"),
|
||||
embedding_mode=os.getenv("LEANN_EMBED_MODE", "sentence-transformers"),
|
||||
graph_degree=32,
|
||||
complexity=64,
|
||||
is_recompute=is_recompute,
|
||||
num_threads=4,
|
||||
**kwargs,
|
||||
)
|
||||
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_group(
|
||||
index_path: str,
|
||||
recompute: bool,
|
||||
query: str,
|
||||
repeats: int,
|
||||
complexity: int = 32,
|
||||
top_k: int = 10,
|
||||
) -> float:
|
||||
# Independent searcher per group; fixed port when recompute
|
||||
searcher = LeannSearcher(index_path=index_path)
|
||||
|
||||
# Warm-up once
|
||||
_ = searcher.search(
|
||||
query,
|
||||
top_k=top_k,
|
||||
complexity=complexity,
|
||||
recompute_embeddings=recompute,
|
||||
)
|
||||
|
||||
def _once() -> float:
|
||||
t0 = time.time()
|
||||
_ = searcher.search(
|
||||
query,
|
||||
top_k=top_k,
|
||||
complexity=complexity,
|
||||
recompute_embeddings=recompute,
|
||||
)
|
||||
return time.time() - t0
|
||||
|
||||
if repeats <= 1:
|
||||
t = _once()
|
||||
else:
|
||||
vals = [_once() for _ in range(repeats)]
|
||||
vals.sort()
|
||||
t = vals[len(vals) // 2]
|
||||
|
||||
searcher.cleanup()
|
||||
return t
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--num-docs", type=int, default=5000)
|
||||
parser.add_argument("--repeats", type=int, default=3)
|
||||
parser.add_argument("--complexity", type=int, default=32)
|
||||
args = parser.parse_args()
|
||||
|
||||
base = Path.cwd() / ".leann" / "indexes" / f"bench_n{args.num_docs}"
|
||||
base.parent.mkdir(parents=True, exist_ok=True)
|
||||
# ---------- Build HNSW variants ----------
|
||||
hnsw_r = str(base / f"hnsw_recompute_n{args.num_docs}.leann")
|
||||
hnsw_nr = str(base / f"hnsw_norecompute_n{args.num_docs}.leann")
|
||||
ensure_index(hnsw_r, "hnsw", args.num_docs, True)
|
||||
ensure_index(hnsw_nr, "hnsw", args.num_docs, False)
|
||||
|
||||
# ---------- Build DiskANN variants ----------
|
||||
diskann_r = str(base / "diskann_r.leann")
|
||||
diskann_nr = str(base / "diskann_nr.leann")
|
||||
ensure_index(diskann_r, "diskann", args.num_docs, True)
|
||||
ensure_index(diskann_nr, "diskann", args.num_docs, False)
|
||||
|
||||
# ---------- Helpers ----------
|
||||
def _size_for(prefix: str) -> int:
|
||||
p = Path(prefix)
|
||||
base_dir = p.parent
|
||||
stem = p.stem
|
||||
total = 0
|
||||
for f in base_dir.iterdir():
|
||||
if f.is_file() and f.name.startswith(stem):
|
||||
total += f.stat().st_size
|
||||
return total
|
||||
|
||||
# ---------- HNSW benchmark ----------
|
||||
t_hnsw_r = _bench_group(
|
||||
hnsw_r, True, "test document number 42", repeats=args.repeats, complexity=args.complexity
|
||||
)
|
||||
t_hnsw_nr = _bench_group(
|
||||
hnsw_nr, False, "test document number 42", repeats=args.repeats, complexity=args.complexity
|
||||
)
|
||||
size_hnsw_r = _size_for(hnsw_r)
|
||||
size_hnsw_nr = _size_for(hnsw_nr)
|
||||
|
||||
print("Benchmark results (HNSW):")
|
||||
print(f" recompute=True: search_time={t_hnsw_r:.3f}s, size={size_hnsw_r / 1024 / 1024:.1f}MB")
|
||||
print(
|
||||
f" recompute=False: search_time={t_hnsw_nr:.3f}s, size={size_hnsw_nr / 1024 / 1024:.1f}MB"
|
||||
)
|
||||
print(" Expectation: no-recompute should be faster but larger on disk.")
|
||||
|
||||
# ---------- DiskANN benchmark ----------
|
||||
t_diskann_r = _bench_group(
|
||||
diskann_r, True, "DiskANN R test doc 123", repeats=args.repeats, complexity=args.complexity
|
||||
)
|
||||
t_diskann_nr = _bench_group(
|
||||
diskann_nr,
|
||||
False,
|
||||
"DiskANN NR test doc 123",
|
||||
repeats=args.repeats,
|
||||
complexity=args.complexity,
|
||||
)
|
||||
size_diskann_r = _size_for(diskann_r)
|
||||
size_diskann_nr = _size_for(diskann_nr)
|
||||
|
||||
print("\nBenchmark results (DiskANN):")
|
||||
print(f" build(recompute=True, partition): size={size_diskann_r / 1024 / 1024:.1f}MB")
|
||||
print(f" build(recompute=False): size={size_diskann_nr / 1024 / 1024:.1f}MB")
|
||||
print(f" search recompute=True (final rerank): {t_diskann_r:.3f}s")
|
||||
print(f" search recompute=False (PQ only): {t_diskann_nr:.3f}s")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -10,6 +10,7 @@ This benchmark compares search performance between DiskANN and HNSW backends:
|
||||
"""
|
||||
|
||||
import gc
|
||||
import multiprocessing as mp
|
||||
import tempfile
|
||||
import time
|
||||
from pathlib import Path
|
||||
@@ -17,6 +18,12 @@ from typing import Any
|
||||
|
||||
import numpy as np
|
||||
|
||||
# Prefer 'fork' start method to avoid POSIX semaphore leaks on macOS
|
||||
try:
|
||||
mp.set_start_method("fork", force=True)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def create_test_texts(n_docs: int) -> list[str]:
|
||||
"""Create synthetic test documents for benchmarking."""
|
||||
@@ -113,10 +120,10 @@ def benchmark_backend(
|
||||
]
|
||||
score_validity_rate = len(valid_scores) / len(all_scores) if all_scores else 0
|
||||
|
||||
# Clean up
|
||||
# Clean up (ensure embedding server shutdown and object GC)
|
||||
try:
|
||||
if hasattr(searcher, "__del__"):
|
||||
searcher.__del__()
|
||||
if hasattr(searcher, "cleanup"):
|
||||
searcher.cleanup()
|
||||
del searcher
|
||||
del builder
|
||||
gc.collect()
|
||||
@@ -259,10 +266,21 @@ if __name__ == "__main__":
|
||||
print(f"\n❌ Benchmark failed: {e}")
|
||||
sys.exit(1)
|
||||
finally:
|
||||
# Ensure clean exit
|
||||
# Ensure clean exit (forceful to prevent rare hangs from atexit/threads)
|
||||
try:
|
||||
gc.collect()
|
||||
print("\n🧹 Cleanup completed")
|
||||
# Flush stdio to ensure message is visible before hard-exit
|
||||
try:
|
||||
import sys as _sys
|
||||
|
||||
_sys.stdout.flush()
|
||||
_sys.stderr.flush()
|
||||
except Exception:
|
||||
pass
|
||||
except Exception:
|
||||
pass
|
||||
sys.exit(0)
|
||||
# Use os._exit to bypass atexit handlers that may hang in rare cases
|
||||
import os as _os
|
||||
|
||||
_os._exit(0)
|
||||
|
||||
Reference in New Issue
Block a user