Interface SqlVectorStoreConfig

Configuration for SQL-backed vector store.

SqlVectorStoreConfig

interface SqlVectorStoreConfig {
    id: string;
    customProps?: Record<string, any>;
    type: "sql";
    storage?: StorageResolutionOptions;
    adapter?: StorageAdapter;
    defaultEmbeddingDimension?: number;
    similarityMetric?: "cosine" | "euclidean" | "dotproduct";
    enableFullTextSearch?: boolean;
    tablePrefix?: string;
}

Hierarchy (view full)

Properties

id: string

A unique identifier for this specific provider instance (e.g., "pinecone-main-prod", "weaviate-dev-local"). This ID is used by the VectorStoreManager to retrieve this provider.

customProps?: Record<string, any>

Any other custom properties or configurations specific to this provider instance not covered by standard fields.

type: "sql"

Must be 'sql' for this provider

storage?: StorageResolutionOptions

Storage adapter configuration. Passed directly to resolveStorageAdapter().

adapter?: StorageAdapter

Pre-initialized storage adapter. If provided, storage config is ignored.

defaultEmbeddingDimension?: number

Default embedding dimension for new collections.

similarityMetric?: "cosine" | "euclidean" | "dotproduct"

Default similarity metric.

Default

'cosine'
enableFullTextSearch?: boolean

Enable full-text search indexing. Creates FTS5 virtual tables for SQLite or tsvector columns for PostgreSQL.

Default

true
tablePrefix?: string

Table name prefix for all vector store tables.

Default

'agentos_rag_'