surrealdb-vector

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

SurrealDB Vector Search

SurrealDB 向量搜索

HNSW Index

HNSW 索引

Create a basic HNSW index:

surql

DEFINE INDEX hnsw_idx ON pts FIELDS point HNSW DIMENSION 4;

With specific distance function and type:

surql

DEFINE INDEX hnsw_idx ON pts FIELDS point HNSW DIMENSION 4 DIST EUCLIDEAN TYPE F64;

Available types:

F64

F32

I64

I32

I16

创建基础HNSW索引：

surql

DEFINE INDEX hnsw_idx ON pts FIELDS point HNSW DIMENSION 4;

指定距离函数和类型：

surql

DEFINE INDEX hnsw_idx ON pts FIELDS point HNSW DIMENSION 4 DIST EUCLIDEAN TYPE F64;

支持的类型：

F64

F32

I64

I32

I16

Full Table Example

完整表示例

surql

DEFINE TABLE OVERWRITE document SCHEMALESS;
DEFINE FIELD OVERWRITE embedding ON document TYPE array<float>;
DEFINE INDEX OVERWRITE hnsw_idx_document ON document
    FIELDS embedding
    HNSW DIMENSION 384
    DIST COSINE
    TYPE F32
    EFC 150 M 12 M0 24;

surql

DEFINE TABLE OVERWRITE document SCHEMALESS;
DEFINE FIELD OVERWRITE embedding ON document TYPE array<float>;
DEFINE INDEX OVERWRITE hnsw_idx_document ON document
    FIELDS embedding
    HNSW DIMENSION 384
    DIST COSINE
    TYPE F32
    EFC 150 M 12 M0 24;

HNSW Parameters

HNSW 参数

Parameter	Description
DIMENSION	Vector dimensionality (must match your embeddings)
DIST	Distance function: `COSINE` , `EUCLIDEAN` , etc.
TYPE	Numeric type: `F64` , `F32` , `I64` , `I32` , `I16`
EFC	Construction search effort (higher = better index)
M	Max connections per node
M0	Max connections at layer 0

参数	描述
DIMENSION	向量维度（必须与你的embeddings匹配）
DIST	距离函数： `COSINE` , `EUCLIDEAN` 等
TYPE	数值类型： `F64` , `F32` , `I64` , `I32` , `I16`
EFC	构建索引时的搜索力度（值越高，索引质量越好）
M	每个节点的最大连接数
M0	第0层的最大连接数

Querying Vectors

向量查询

The

<|K, EF|>

operator performs KNN search.

is the number of results,

EF

is the search effort (higher = more accurate, slower).

Recommended effort values:

```
40
```
— default, good accuracy
```
17
```
— fast but may miss some results

<|K, EF|>

运算符用于执行KNN搜索。

是返回结果的数量，

EF

是搜索力度（值越高，结果越准确，但速度越慢）。

推荐的力度值：

```
40
```
— 默认值，准确性良好
```
17
```
— 速度快，但可能遗漏部分结果

Basic KNN Query

基础KNN查询

surql

SELECT
    *,
    vector::distance::knn() AS dist
FROM document
WHERE embedding <|10, 40|> $vector;

vector::distance::knn()

uses the distance function defined by the index.

surql

SELECT
    *,
    vector::distance::knn() AS dist
FROM document
WHERE embedding <|10, 40|> $vector;

vector::distance::knn()

会使用索引定义的距离函数。

Scored Results with Threshold

带阈值的评分结果

surql

SELECT *, score
FROM (
    SELECT *, (1 - vector::distance::knn()) AS score
    FROM document
    WHERE embedding <|20, 40|> $vector
)
WHERE score >= $threshold
ORDER BY score DESC;

surql

SELECT *, score
FROM (
    SELECT *, (1 - vector::distance::knn()) AS score
    FROM document
    WHERE embedding <|20, 40|> $vector
)
WHERE score >= $threshold
ORDER BY score DESC;