Class WeaviateStore

constructor

• new WeaviateStore(embeddings, args): WeaviateStore

• Parameters

  • embeddings: EmbeddingsInterface
  • args: WeaviateLibArgs

  Returns WeaviateStore

FilterType

addDocuments

• addDocuments(documents, options?): Promise<string[]>

• Method to add documents to the Weaviate index. It first generates vectors for the documents using the embeddings, then adds the vectors and documents to the index.

  Parameters

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

    Array of documents to be added.
  • Optionaloptions: {
        ids?: string[];
    }

    Optional parameter that can include specific IDs for the documents.

    • Optionalids?: string[]

  Returns Promise<string[]>

  An array of document IDs.

addVectors

• addVectors(vectors, documents, options?): Promise<string[]>

• Method to add vectors and corresponding documents to the Weaviate index.

  Parameters

  • vectors: number[][]

    Array of vectors to be added.
  • documents: Document<Record<string, any>>[]

    Array of documents corresponding to the vectors.
  • Optionaloptions: {
        ids?: string[];
    }

    Optional parameter that can include specific IDs for the documents.

    • Optionalids?: string[]

  Returns Promise<string[]>

  An array of document IDs.

delete

• delete(params): Promise<void>

• Method to delete data from the Weaviate index. It can delete data based on specific IDs or a filter.

  Parameters

  • params: {
        filter?: WeaviateFilter;
        ids?: string[];
    }

    Object that includes either an array of IDs or a filter for the data to be deleted.

    • Optionalfilter?: WeaviateFilter

    • Optionalids?: string[]

  Returns Promise<void>

  Promise that resolves when the deletion is complete.

maxMarginalRelevanceSearch

• maxMarginalRelevanceSearch(query, options, _callbacks?): Promise<Document<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<WeaviateFilter>
  • Optional_callbacks: undefined

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

  • List of documents selected by maximal marginal relevance.

similaritySearchVectorWithScore

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

• Method to perform a similarity search on the stored vectors in the Weaviate index. It returns the top k most similar documents and their similarity scores.

  Parameters

  • query: number[]

    The query vector.
  • k: number

    The number of most similar documents to return.
  • Optionalfilter: WeaviateFilter

    Optional filter to apply to the search.

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

  An array of tuples, where each tuple contains a document and its similarity score.

similaritySearchVectorWithScoreAndEmbedding

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

• Method to perform a similarity search on the stored vectors in the Weaviate index. It returns the top k most similar documents, their similarity scores and embedding vectors.

  Parameters

  • query: number[]

    The query vector.
  • k: number

    The number of most similar documents to return.
  • Optionalfilter: WeaviateFilter

    Optional filter to apply to the search.

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

  An array of tuples, where each tuple contains a document, its similarity score and its embedding vector.

StaticfromDocuments

• fromDocuments(docs, embeddings, args): Promise<WeaviateStore>

• Static method to create a new WeaviateStore instance from a list of documents. It adds the documents to the Weaviate index.

  Parameters

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

    Array of documents.
  • embeddings: EmbeddingsInterface

    Embeddings to be used for the documents.
  • args: WeaviateLibArgs

    Arguments required to create a new WeaviateStore instance.

  Returns Promise<WeaviateStore>

  A new WeaviateStore instance.

StaticfromExistingIndex

• fromExistingIndex(embeddings, args): Promise<WeaviateStore>

• Static method to create a new WeaviateStore instance from an existing Weaviate index.

  Parameters

  • embeddings: EmbeddingsInterface

    Embeddings to be used for the Weaviate index.
  • args: WeaviateLibArgs

    Arguments required to create a new WeaviateStore instance.

  Returns Promise<WeaviateStore>

  A new WeaviateStore instance.

StaticfromTexts

• fromTexts(texts, metadatas, embeddings, args): Promise<WeaviateStore>

• Static method to create a new WeaviateStore instance from a list of texts. It first creates documents from the texts and metadata, then adds the documents to the Weaviate index.

  Parameters

  • texts: string[]

    Array of texts.
  • metadatas: object | object[]

    Metadata for the texts. Can be a single object or an array of objects.
  • embeddings: EmbeddingsInterface

    Embeddings to be used for the texts.
  • args: WeaviateLibArgs

    Arguments required to create a new WeaviateStore instance.

  Returns Promise<WeaviateStore>

  A new WeaviateStore instance.