Execute multiple operations in a single batch.
Get statistics about the store.
Protected
hybridPerforms hybrid search combining vector similarity and text search.
The namespace prefix to search within
The text query to search for
Optional
options: { Search options including filter, vector weight, and similarity threshold
Optional
filter?: Record<string, unknown>Optional
limit?: numberOptional
offset?: numberOptional
similarityOptional
vectorPromise resolving to an array of search results with combined similarity scores
List namespaces with optional filtering.
Optional
options: { Optional
limit?: numberOptional
maxOptional
offset?: numberOptional
prefix?: string[]Optional
suffix?: string[]Search for items in the store with support for text search, vector search, and filtering.
The namespace prefix to search within
Optional
options: { Search options including search mode, filters, query text, and pagination
Optional
distanceDistance metric for vector search.
"cosine"
Optional
filter?: Record<string, null | string | number | boolean | FilterOperators>Filter conditions with support for advanced operators.
Optional
limit?: numberMaximum number of results to return.
10
Optional
mode?: "text" | "vector" | "hybrid" | "auto"Search mode.
"auto"
Optional
offset?: numberNumber of results to skip for pagination.
0
Optional
query?: stringNatural language search query.
Optional
refreshWhether to refresh TTL for returned items.
Optional
similaritySimilarity threshold for vector search.
Optional
vectorWeight for vector search in hybrid mode.
0.7
Promise resolving to an array of search results with optional similarity scores
// Basic text search
const results = await store.search(["documents"], {
query: "machine learning",
mode: "text"
});
// Vector search
const results = await store.search(["documents"], {
query: "machine learning",
mode: "vector",
similarityThreshold: 0.7
});
// Hybrid search (combining vector and text)
const results = await store.search(["documents"], {
query: "machine learning",
mode: "hybrid",
vectorWeight: 0.7
});
// Filtered search
const results = await store.search(["products"], {
filter: { category: "electronics", price: { $lt: 100 } }
});
Protected
vectorPerforms vector similarity search using embeddings.
The namespace prefix to search within
The text query to embed and search for similar items
Optional
options: { Search options including filter, similarity threshold, and distance metric
Optional
distanceOptional
filter?: Record<string, unknown>Optional
limit?: numberOptional
offset?: numberOptional
similarityPromise resolving to an array of search results with similarity scores
Static
fromCreates a PostgresStore instance from a connection string.
Optional
options: Omit<PostgresStoreConfig, "connectionOptions">
PostgreSQL implementation of the BaseStore interface. This is now a lightweight orchestrator that delegates to specialized modules.