Class RocksetStore

constructor

• new RocksetStore(
      embeddings: EmbeddingsInterface,
      args: RocksetLibArgs,
  ): RocksetStore

  Constructs a new RocksetStore

  Parameters

  • embeddings: EmbeddingsInterface

    Object used to embed queries and page content

  • args: RocksetLibArgs

  Returns RocksetStore

client

collectionName

embeddingKey

Optionalfilter

FilterType

textKey

workspaceName

similarityMetric

• get similarityMetric(): SimilarityMetric

  Returns SimilarityMetric

• set similarityMetric(metric: SimilarityMetric): void

  Parameters

  • metric: SimilarityMetric

  Returns void

_vectorstoreType

• _vectorstoreType(): "rockset"

  Gets a string representation of the type of this VectorStore

  Returns "rockset"

addDocuments

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

  Embeds and adds Documents to the store.

  Parameters

  • documents: Document[]

    The documents to store

  Returns Promise<undefined | string[]>

  The _id's of the documents added

addVectors

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

  Adds vectors to the store given their corresponding Documents

  Parameters

  • vectors: number[][]

    The vectors to store

  • documents: Document[]

    The Documents they represent

  Returns Promise<undefined | string[]>

  The _id's of the added documents

delete

• delete(ids: string[]): Promise<void>

  Deletes Rockset documements given their _id's

  Parameters

  • ids: string[]

    The IDS to remove documents with

  Returns Promise<void>

destroy

• destroy(waitUntilDeletion?: boolean): 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>

similaritySearchVectorWithScore

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

StaticfromDocuments

• fromDocuments(
      docs: Document[],
      embeddings: EmbeddingsInterface,
      dbConfig: RocksetLibArgs,
  ): Promise<RocksetStore>

  Constructs, adds docs to, and returns a RocksetStore object

  Parameters

  • docs: Document[]

    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: string[],
      metadatas: object | object[],
      embeddings: EmbeddingsInterface,
      dbConfig: RocksetLibArgs,
  ): 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

• withNewCollection(
      embeddings: EmbeddingsInterface,
      dbConfig: RocksetLibArgs,
      collectionOptions?: CreateCollectionRequest,
  ): Promise<RocksetStore>

  Creates a new Rockset collection and returns a RocksetStore that uses it

  Parameters

  • embeddings: EmbeddingsInterface

    Object used to embed queries and page content

  • dbConfig: RocksetLibArgs

    The options to be passed into the RocksetStore constructor

  • OptionalcollectionOptions: CreateCollectionRequest

    The arguments to sent with the HTTP request when creating the collection. Setting a field mapping that VECTOR_ENFORCEs is recommended when using this function. See https://rockset.com/docs/vector-functions/#vector_enforce

  Returns Promise<RocksetStore>