Class UpstashVectorStore

The main class that extends the 'VectorStore' class. It provides methods for interacting with Upstash index, such as adding documents, deleting documents, performing similarity search and more.

Hierarchy

  • VectorStore
    • UpstashVectorStore

Constructors

constructor

Properties

FilterType caller embeddings filter? index namespace? useUpstashEmbeddings?

Methods

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

Constructors

constructor

Properties

FilterType

FilterType: string

caller

caller: AsyncCaller

embeddings

embeddings: EmbeddingsInterface

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

Optionalfilter

filter?: string

index

index: Index<Dict>

Optionalnamespace

namespace?: string

OptionaluseUpstashEmbeddings

useUpstashEmbeddings?: boolean

Methods

addDocuments

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

  • This method adds documents to Upstash database. Documents are first converted to vectors using the provided embeddings instance, and then upserted to the database.

    Parameters

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

      Array of Document objects to be added to the database.

    • Optionaloptions: {
          ids?: string[];
          useUpstashEmbeddings?: boolean;
      }

      Optional object containing array of ids for the documents.

      • Optionalids?: string[]
      • OptionaluseUpstashEmbeddings?: boolean

    Returns Promise<string[]>

    Promise that resolves with the ids of the provided documents when the upsert operation is done.

addVectors

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

  • This method adds the provided vectors to Upstash database.

    Parameters

    • vectors: number[][]

      Array of vectors to be added to the Upstash database.

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

      Array of Document objects, each associated with a vector.

    • Optionaloptions: {
          ids?: string[];
      }

      Optional object containing the array of ids foor the vectors.

      • Optionalids?: string[]

    Returns Promise<string[]>

    Promise that resolves with the ids of the provided documents when the upsert operation is done.

asRetriever

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

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

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

      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<UpstashVectorStore>

    • 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

  • delete(params): Promise<void>

  • This method deletes documents from the Upstash database. You can either provide the target ids, or delete all vectors in the database.

    Parameters

    • params: UpstashDeleteParams

      Object containing either array of ids of the documents or boolean deleteAll.

    Returns Promise<void>

    Promise that resolves when the specified documents have been deleted from the database.

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

  • This method performs a similarity search in the Upstash database over the existing vectors.

    Parameters

    • query: string | number[]

      Query vector for the similarity search.

    • k: number

      The number of similar vectors to return as result.

    • Optionalfilter: string

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

    Promise that resolves with an array of tuples, each containing Document object and similarity score. The length of the result will be maximum of 'k' and vectors in the index.

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<UpstashVectorStore>

  • This method creates a new UpstashVector instance from an array of Document instances.

    Parameters

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

      The docs to be added to Upstash database.

    • embeddings: EmbeddingsInterface

      Embedding interface of choice, to create the embeddings.

    • dbConfig: UpstashVectorLibArgs

      Object containing the Upstash database configs.

    Returns Promise<UpstashVectorStore>

    Promise that resolves with a new UpstashVector instance

StaticfromExistingIndex

StaticfromTexts

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

  • This method creates a new UpstashVector instance from an array of texts. The texts are initially converted to Document instances and added to Upstash database.

    Parameters

    • texts: string[]

      The texts to create the documents from.

    • metadatas: UpstashMetadata | UpstashMetadata[]

      The metadata values associated with the texts.

    • embeddings: EmbeddingsInterface

      Embedding interface of choice, to create the text embeddings.

    • dbConfig: UpstashVectorLibArgs

      Object containing the Upstash database configs.

    Returns Promise<UpstashVectorStore>

    Promise that resolves with a new UpstashVector instance.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods