Class SqlVectorStore

SQL-backed vector store implementation.

Uses @framers/sql-storage-adapter for cross-platform persistence. Stores embeddings as JSON blobs and computes similarity in application code (with optional native vector extensions for PostgreSQL).

SqlVectorStore

Implements

Example

const store = new SqlVectorStore();

await store.initialize({
  id: 'sql-vector-store',
  type: 'sql',
  storage: {
    filePath: './vectors.db',
    priority: ['better-sqlite3', 'sqljs']
  },
  enableFullTextSearch: true
});

// Create a collection
await store.createCollection('documents', 1536);

// Upsert documents
await store.upsert('documents', [{
  id: 'doc-1',
  embedding: [...], // 1536-dim vector
  textContent: 'Example document content',
  metadata: { author: 'Alice', category: 'tech' }
}]);

// Query by similarity
const results = await store.query('documents', queryEmbedding, { topK: 5 });

Implements

IVectorStore

Index

Constructors

constructor

Methods

initialize createCollection collectionExists deleteCollection upsert query hybridSearch delete checkHealth shutdown getStats

Constructors

constructor

new SqlVectorStore(): SqlVectorStore
Constructs a SqlVectorStore instance. The store is not operational until initialize() is called.

Returns SqlVectorStore
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:195

Methods

initialize

initialize(config): Promise<void>
Initializes the vector store with the provided configuration.

Creates necessary tables and indexes if they don't exist.
Parameters
- config: VectorStoreProviderConfig
  Configuration object
Returns Promise<void>
Throws
If configuration is invalid or initialization fails
Implementation of IVectorStore.initialize
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:207

createCollection

createCollection(collectionName, dimension, options?): Promise<void>
Creates a new collection for storing vectors.
Parameters
- collectionName: string
  Unique name for the collection
- dimension: number
  Vector embedding dimension
- Optional options: CreateCollectionOptions
  Creation options
Returns Promise<void>
Implementation of IVectorStore.createCollection
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:324

collectionExists

collectionExists(collectionName): Promise<boolean>
Checks if a collection exists.
Parameters
- collectionName: string
  Collection name to check
Returns Promise<boolean>
True if collection exists
Implementation of IVectorStore.collectionExists
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:371

deleteCollection

deleteCollection(collectionName): Promise<void>
Deletes a collection and all its documents.
Parameters
- collectionName: string
  Collection to delete
Returns Promise<void>
Implementation of IVectorStore.deleteCollection
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:387

upsert

upsert(collectionName, documents, options?): Promise<UpsertResult>
Upserts documents into a collection.
Parameters
- collectionName: string
  Target collection
- documents: VectorDocument[]
  Documents to upsert
- Optional options: UpsertOptions
  Upsert options
Returns Promise<UpsertResult>
Result of the upsert operation
Implementation of IVectorStore.upsert
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:441

query

query(collectionName, queryEmbedding, options?): Promise<QueryResult>
Queries a collection for similar documents.
Parameters
- collectionName: string
  Collection to query
- queryEmbedding: number[]
  Query vector
- Optional options: QueryOptions
  Query options
Returns Promise<QueryResult>
Query results sorted by similarity
Implementation of IVectorStore.query
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:537

hybridSearch

hybridSearch(collectionName, queryEmbedding, queryText, options?): Promise<QueryResult>
Performs hybrid search combining vector similarity with keyword matching.
Parameters
- collectionName: string
  Collection to search
- queryEmbedding: number[]
  Query vector for semantic search
- queryText: string
  Text query for keyword search
- Optional options: QueryOptions & {
  alpha?: number;
  }
  Search options
Returns Promise<QueryResult>
Combined search results
Example
```
const results = await store.hybridSearch(
  'documents',
  queryEmbedding,
  'machine learning tutorial',
  { topK: 10, alpha: 0.7 } // 70% vector, 30% keyword
);
```
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:649

delete

delete(collectionName, ids?, options?): Promise<DeleteResult>
Deletes documents from a collection.
Parameters
- collectionName: string
  Collection to delete from
- Optional ids: string[]
  Specific document IDs to delete
- Optional options: DeleteOptions
  Delete options (filter, deleteAll)
Returns Promise<DeleteResult>
Deletion result
Implementation of IVectorStore.delete
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:727

checkHealth

checkHealth(): Promise<{
isHealthy: boolean;
details?: any;
}>
Checks the health of the vector store.

Returns Promise<{
isHealthy: boolean;
details?: any;
}>
Health status
Implementation of IVectorStore.checkHealth
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:801

shutdown

shutdown(): Promise<void>
Gracefully shuts down the vector store.

Returns Promise<void>
Implementation of IVectorStore.shutdown
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:837

getStats

getStats(collectionName?): Promise<Record<string, any>>
Gets statistics for a collection or the entire store.
Parameters
- Optional collectionName: string
  Specific collection, or all if omitted
Returns Promise<Record<string, any>>
Statistics
Implementation of IVectorStore.getStats
- Defined in rag/implementations/vector_stores/SqlVectorStore.ts:856

Class SqlVectorStore

Implements

Example

Implements

Index

Constructors

Methods

Constructors

constructor

Returns SqlVectorStore

Methods

initialize

Parameters

Returns Promise<void>

Throws

createCollection

Parameters

Returns Promise<void>

collectionExists

Parameters

Returns Promise<boolean>

deleteCollection

Parameters

Returns Promise<void>

upsert

Parameters

Returns Promise<UpsertResult>

query

Parameters

Returns Promise<QueryResult>

hybridSearch

Parameters

Returns Promise<QueryResult>

Example

delete

Parameters

Returns Promise<DeleteResult>

checkHealth

Returns Promise<{ isHealthy: boolean; details?: any; }>

shutdown

Returns Promise<void>

getStats

Parameters

Returns Promise<Record<string, any>>

Settings

Member Visibility

Theme

On This Page

Returns Promise<{
isHealthy: boolean;
details?: any;
}>