knn_search
Find similar items using vector similarity search in Easysearch MCP Server. Input a vector to retrieve nearest neighbors from specified indexes with configurable filters and result counts.
Instructions
K近邻向量搜索
参数:
index: 索引名称
field: 向量字段名
query_vector: 查询向量
k: 返回最近邻数量
num_candidates: 候选数量
filter: 过滤条件
示例:
knn_search("products", "embedding", [0.1, 0.2, 0.3, ...], k=10)
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| index | Yes | ||
| field | Yes | ||
| query_vector | Yes | ||
| k | No | ||
| num_candidates | No | ||
| filter | No |