技能版本 1.0.0
vector-index-tuning
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
价格
免费
- 安装：免费
在组织开通时一次性收取；再次读取清单或下载不重复收费。
以上为公开标价。你的组织可能有协议价，以控制台显示的价格为准。
如何使用
为组织安装
开通即安装：组织固定使用开通时的版本（当前为 1.0.0）。升级到新版本需要取消后重新开通。
创建凭证
客户端使用组织凭证读取；绑定到数字人后，数字人使用绑定凭证按需加载。请求中携带：
Authorization: Bearer $ZGI_MARKET_KEY读取清单与安装包
清单列出版本、文件和校验值；安装包是一个 zip 文件。
读取清单 curl "https://market-api.zgi.im/v1/market/skills/vector-index-tuning/manifest" \ -H "Authorization: Bearer $ZGI_MARKET_KEY"下载安装包 curl "https://market-api.zgi.im/v1/market/skills/vector-index-tuning/package" \ -H "Authorization: Bearer $ZGI_MARKET_KEY" \ -o vector-index-tuning.zip读取清单和下载安装包不计入用量。下载后请用响应头中的 SHA-256 校验文件。
技能说明
- 名称
- vector-index-tuning
- 说明
- Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
仅指令
技能包内没有脚本文件：这个技能是供模型阅读的文本。
SKILL.md 节选
# 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
| Parameter | Default | Effect |
|-----------|---------|--------|
| **M** | 16 | Connections per node, ↑ = better recall, more memory |
| **efConstruction** | 100 | Build quality, ↑ = better index, slower build |
| **efSearch** | 50 | Search quality, ↑ = better recall, slower search |
### 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
```python
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 = 64SKILL.md 不止这些内容，安装后可阅读全文。
技能包内容
共 1 个文件，合计 14.9 KiB
- SKILL.md14.9 KiB
来源与审核
- 审核状态
- 尚未审核，内容来自上游来源
- 许可证
- 未说明
审核状态是平台对上架信息的记录，不构成对上游服务质量或可用性的担保。