30 lines
926 B
Markdown
30 lines
926 B
Markdown
|
|
# 向量存储配置
|
|||
|
|
|
|||
|
|
除了记忆存储适配器外,Mastra 还提供向量存储适配器,用于存储和检索向量嵌入。其中之一是 `LibSQLVector` 适配器,它为在 LibSQL 向量数据库中存储和检索向量嵌入提供简单的接口。
|
|||
|
|
|
|||
|
|
```typescript
|
|||
|
|
import { Memory } from "@mastra/memory";
|
|||
|
|
import { LibSQLStore, LibSQLVector } from "@mastra/libsql";
|
|||
|
|
|
|||
|
|
const memory = new Memory({
|
|||
|
|
storage: new LibSQLStore({
|
|||
|
|
id: "learning-memory-storage",
|
|||
|
|
url: "file:../../memory.db", // 相对于 `.mastra/output` 目录的相对路径
|
|||
|
|
}),
|
|||
|
|
vector: new LibSQLVector({
|
|||
|
|
id: "learning-memory-vector",
|
|||
|
|
connectionUrl: "file:../../vector.db", // 相对于 `.mastra/output` 目录的相对路径
|
|||
|
|
}),
|
|||
|
|
});
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
Mastra 支持多种向量存储选项,包括:
|
|||
|
|
|
|||
|
|
- LibSQL
|
|||
|
|
- Chroma
|
|||
|
|
- Pinecone
|
|||
|
|
- Qdrant
|
|||
|
|
- Postgres(使用 pgvector)
|
|||
|
|
|
|||
|
|
向量存储负责存储和检索用于语义搜索的向量嵌入。
|