Details

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"
    }

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

from qdrant_client import QdrantClient
from qdrant_client.http import models

def create_optimized_collection(
    client: QdrantClient,
    collection_name: str,
    vector_size: int,
    num_vectors: int,
    optimize_for: str = "balanced"  # "recall", "speed", "memory"
) -> None:
    """Create collection with optimized settings."""

    # HNSW configuration based on optimization target
    hnsw_configs = {

import time
from dataclasses import dataclass
from typing import List
import numpy as np

@dataclass
class SearchMetrics:
    latency_p50_ms: float
    latency_p95_ms: float
    latency_p99_ms: float
    recall: float
    qps: float


class VectorSearchMonitor:
    """Monitor vector search performance."""

    def __init__(self, ground_truth_fn=None):
        self.latencies = []
        self.recalls = []
        self.ground_truth_fn = ground_truth_fn

    def measure_search(
        self,
        search_fn,
        query_vectors: np.ndarray,
        k: int = 10,
        num_iterations: int = 100
    ) -> SearchMetrics:
        """Benchmark search performance."""
        latencies = []

        for _ in range(num_iterations):
            for query in query_vectors:
                start = time.perf_counter()
                results = search_fn(query, k=k)
                latency = (time.perf_counter() - start) * 1000
                latencies.append(latency)

        latencies = np.array(latencies)
        total_queries = num_iterations * len(query_vectors)
        total_time = sum(latencies) / 1000  # seconds

        return SearchMetrics(
            latency_p50_ms=np.percentile(latencies, 50),
            latency_p95_ms=np.percentile(latencies, 95),
            latency_p99_ms=np.percentile(latencies, 99),
            recall=self._calculate_recall(search_fn, query_vectors, k) if self.ground_truth_fn else 0,
            qps=total_queries / total_time
        )

    def _calculate_recall(self, search_fn, queries: np.ndarray, k: int) -> float:
        """Calculate recall against ground truth."""
        if not self.ground_truth_fn:
            return 0

        correct = 0
        total = 0

        for query in queries:
            predicted = set(search_fn(query, k=k))
            actual = set(self.ground_truth_fn(query, k=k))
            correct += len(predicted & actual)
            total += k

        return correct / total


def profile_index_build(
    build_fn,
    vectors: np.ndarray,
    batch_sizes: List[int] = [1000, 10000, 50000]
) -> dict:
    """Profile index build performance."""
    results = {}

    for batch_size in batch_sizes:
        times = []
        for i in range(0, len(vectors), batch_size):
            batch = vectors[i:i + batch_size]
            start = time.perf_counter()
            build_fn(batch)
            times.append(time.perf_counter() - start)

        results[batch_size] = {
            "avg_batch_time_s": np.mean(times),
            "vectors_per_second": batch_size / np.mean(times)
        }

    return results