Class RocksetStore

Exposes Rockset's vector store/search functionality

Hierarchy

  • VectorStore
    • RocksetStore

Constructors

constructor

Properties

FilterType client collectionName embeddingKey embeddings filter? textKey workspaceName

Accessors

similarityMetric

Methods

addDocuments addVectors asRetriever delete destroy maxMarginalRelevanceSearch? similaritySearch similaritySearchVectorWithScore similaritySearchWithScore toJSON toJSONNotImplemented fromDocuments fromTexts withNewCollection

Constructors

constructor

Properties

FilterType

FilterType: string

client

client: MainApi

collectionName

collectionName: string

embeddingKey

embeddingKey: string

embeddings

embeddings: EmbeddingsInterface

Embeddings interface for generating vector embeddings from text queries, enabling vector-based similarity searches.

Optionalfilter

filter?: string

textKey

textKey: string

workspaceName

workspaceName: string

Accessors

similarityMetric

Methods

addDocuments

  • addDocuments(documents): Promise<undefined | string[]>

  • Embeds and adds Documents to the store.

    Parameters

    • documents: Document<Record<string, any>>[]

      The documents to store

    Returns Promise<undefined | string[]>

    The _id's of the documents added

addVectors

  • addVectors(vectors, documents): Promise<undefined | string[]>

  • Adds vectors to the store given their corresponding Documents

    Parameters

    • vectors: number[][]

      The vectors to store

    • documents: Document<Record<string, any>>[]

      The Documents they represent

    Returns Promise<undefined | string[]>

    The _id's of the added documents

asRetriever

  • asRetriever(kOrFields?, filter?, callbacks?, tags?, metadata?, verbose?): VectorStoreRetriever<RocksetStore>

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

    • OptionalkOrFields: number | Partial<VectorStoreRetrieverInput<RocksetStore>>

      If a number is provided, it sets the k parameter (number of items to retrieve).

      • If an object is provided, it should contain various configuration options.
    • Optionalfilter: string

      Optional filter criteria to limit the items retrieved based on the specified filter type.

    • Optionalcallbacks: Callbacks

      Optional callbacks that may be triggered at specific stages of the retrieval process.

    • Optionaltags: string[]

      Tags to categorize or label the VectorStoreRetriever. Defaults to an empty array if not provided.

    • Optionalmetadata: Record<string, unknown>

      Additional metadata as key-value pairs to add contextual information for the retrieval process.

    • Optionalverbose: boolean

      If true, enables detailed logging for the retrieval process. Defaults to false.

    Returns VectorStoreRetriever<RocksetStore>

    • A configured VectorStoreRetriever instance based on the provided parameters.

    Example

    Basic usage with a k value:

    const retriever = myVectorStore.asRetriever(5);

    Usage with a configuration object:

    const retriever = myVectorStore.asRetriever({
      k: 10,
      filter: myFilter,
      tags: ['example', 'test'],
      verbose: true,
      searchType: 'mmr',
      searchKwargs: { alpha: 0.5 },
    });

delete

destroy

  • destroy(waitUntilDeletion?): Promise<void>

  • Deletes the collection this RocksetStore uses

    Parameters

    • OptionalwaitUntilDeletion: boolean

      Whether to sleep until the collection is ready to be queried

    Returns Promise<void>

OptionalmaxMarginalRelevanceSearch

  • maxMarginalRelevanceSearch(query, options, _callbacks): Promise<DocumentInterface<Record<string, any>>[]>

  • Return documents selected using the maximal marginal relevance. Maximal marginal relevance optimizes for similarity to the query AND diversity among selected documents.

    Parameters

    • query: string

      Text to look up documents similar to.

    • options: MaxMarginalRelevanceSearchOptions<string>
    • _callbacks: undefined | Callbacks

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    • List of documents selected by maximal marginal relevance.

similaritySearch

  • similaritySearch(query, k?, filter?, _callbacks?): Promise<DocumentInterface<Record<string, any>>[]>

  • Searches for documents similar to a text query by embedding the query and performing a similarity search on the resulting vector.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: string

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<DocumentInterface<Record<string, any>>[]>

    A promise resolving to an array of DocumentInterface instances representing similar documents.

similaritySearchVectorWithScore

  • similaritySearchVectorWithScore(query, k, filter?): Promise<[Document<Record<string, any>>, number][]>

  • Gets the most relevant documents to a query along with their similarity score. The returned documents are ordered by similarity (most similar at the first index)

    Parameters

    • query: number[]

      The embedded query to search the store by

    • k: number

      The number of documents to retreive

    • Optionalfilter: string

      The SQL WHERE clause to filter by

    Returns Promise<[Document<Record<string, any>>, number][]>

similaritySearchWithScore

  • similaritySearchWithScore(query, k?, filter?, _callbacks?): Promise<[DocumentInterface<Record<string, any>>, number][]>

  • Searches for documents similar to a text query by embedding the query, and returns results with similarity scores.

    Parameters

    • query: string

      Text query for finding similar documents.

    • Optionalk: number

      Number of similar results to return. Defaults to 4.

    • Optionalfilter: string

      Optional filter based on FilterType.

    • Optional_callbacks: Callbacks

      Optional callbacks for monitoring search progress

    Returns Promise<[DocumentInterface<Record<string, any>>, number][]>

    A promise resolving to an array of tuples, each containing a document and its similarity score.

toJSON

  • toJSON(): Serialized

  • Returns Serialized

toJSONNotImplemented

StaticfromDocuments

  • fromDocuments(docs, embeddings, dbConfig): Promise<RocksetStore>

  • Constructs, adds docs to, and returns a RocksetStore object

    Parameters

    • docs: Document<Record<string, any>>[]

      The Documents to store

    • embeddings: EmbeddingsInterface

      The object used to embed queries and page content

    • dbConfig: RocksetLibArgs

      The options to be passed into the RocksetStore constructor

    Returns Promise<RocksetStore>

StaticfromTexts

  • fromTexts(texts, metadatas, embeddings, dbConfig): Promise<RocksetStore>

  • Constructs and returns a RocksetStore object given texts to store.

    Parameters

    • texts: string[]

      The texts to store

    • metadatas: object | object[]

      The metadatas that correspond to

    • embeddings: EmbeddingsInterface

      The object used to embed queries and page content

    • dbConfig: RocksetLibArgs

      The options to be passed into the RocksetStore constructor

    Returns Promise<RocksetStore>

StaticwithNewCollection

Settings

Member Visibility

On This Page

Constructors
Properties
Accessors
Methods