Vector Index Tuning

Guide to optimizing vector indexes for production performance.

When to Use This Skill

• Tuning HNSW parameters
• Implementing quantization
• Optimizing memory usage
• Reducing search latency
• Balancing recall vs speed
• Scaling to billions of vectors

Core Concepts

1. Index Type Selection

Data Size           Recommended Index
────────────────────────────────────────
< 10K vectors  →    Flat (exact search)
10K - 1M       →    HNSW
1M - 100M      →    HNSW + Quantization
> 100M         →    IVF + PQ or DiskANN

2. HNSW Parameters

3. Quantization Types

Full Precision (FP32): 4 bytes × dimensions
Half Precision (FP16): 2 bytes × dimensions
INT8 Scalar:           1 byte × dimensions
Product Quantization:  ~32-64 bytes total
Binary:                dimensions/8 bytes

Templates

Template 1: HNSW Parameter Tuning

import numpy as np
from typing import List, Tuple
import time

def benchmark_hnsw_parameters(
    vectors: np.ndarray,
    queries: np.ndarray,
    ground_truth: np.ndarray,
    m_values: List[int] = [8, 16, 32, 64],
    ef_construction_values: List[int] = [64, 128, 256],
    ef_search_values: List[int] = [32, 64, 128, 256]
) -> List[dict]:
    """Benchmark different HNSW configurations."""
    import hnswlib

    results = []
    dim = vectors.shape[1]
    n = vectors.shape[0]

    for m in m_values:
        for ef_construction in ef_construction_values:
            # Build index
            index = hnswlib.Index(space='cosine', dim=dim)
            index.init_index(max_elements=n, M=m, ef_construction=ef_construction)

            build_start = time.time()
            index.add_items(vectors)
            build_time = time.time() - build_start

            # Get memory usage
            memory_bytes = index.element_count * (
                dim * 4 +  # Vector storage
                m * 2 * 4  # Graph edges (approximate)
            )

            for ef_search in ef_search_values:
                index.set_ef(ef_search)

                # Measure search
                search_start = time.time()
                labels, distances = index.knn_query(queries, k=10)
                search_time = time.time() - search_start

                # Calculate recall
                recall = calculate_recall(labels, ground_truth, k=10)

                results.append({
                    "M": m,
                    "ef_construction": ef_construction,
                    "ef_search": ef_search,
                    "build_time_s": build_time,
                    "search_time_ms": search_time * 1000 / len(queries),
                    "recall@10": recall,
                    "memory_mb": memory_bytes / 1024 / 1024
                })

    return results


def calculate_recall(predictions: np.ndarray, ground_truth: np.ndarray, k: int) -> float:
    """Calculate recall@k."""
    correct = 0
    for pred, truth in zip(predictions, ground_truth):
        correct += len(set(pred[:k]) & set(truth[:k]))
    return correct / (len(predictions) * k)


def recommend_hnsw_params(
    num_vectors: int,
    target_recall: float = 0.95,
    max_latency_ms: float = 10,
    available_memory_gb: float = 8
) -> dict:
    """Recommend HNSW parameters based on requirements."""

    # Base recommendations
    if num_vectors < 100_000:
        m = 16
        ef_construction = 100
    elif num_vectors < 1_000_000:
        m = 32
        ef_construction = 200
    else:
        m = 48
        ef_construction = 256

    # Adjust ef_search based on recall target
    if target_recall >= 0.99:
        ef_search = 256
    elif target_recall >= 0.95:
        ef_search = 128
    else:
        ef_search = 64

    return {
        "M": m,
        "ef_construction": ef_construction,
        "ef_search": ef_search,
        "notes": f"Estimated for {num_vectors:,} vectors, {target_recall:.0%} recall"
    }

Template 2: Quantization Strategies

import numpy as np
from typing import Optional

class VectorQuantizer:
    """Quantization strategies for vector compression."""

    @staticmethod
    def scalar_quantize_int8(
        vectors: np.ndarray,
        min_val: Optional[float] = None,
        max_val: Optional[float] = None
    ) -> Tuple[np.ndarray, dict]:
        """Scalar quantization to INT8."""
        if min_val is None:
            min_val = vectors.min()
        if max_val is