Class Typesense

Typesense vector store.

Hierarchy

  • VectorStore
    • Typesense

Constructors

constructor

Properties

FilterType embeddings

Methods

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

Constructors

constructor

Properties

FilterType

FilterType: Partial<MultiSearchRequestSchema>

embeddings

embeddings: EmbeddingsInterface

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

Methods

addDocuments

  • addDocuments(documents): Promise<void>

  • Add documents to the vector store. Will be updated if in the metadata there is a document with the same id if is using the default import function. Metadata will be added in the columns of the schema based on metadataColumnNames.

    Parameters

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

      Documents to add.

    Returns Promise<void>

addVectors

  • addVectors(vectors, documents): Promise<void>

  • Adds vectors to the vector store.

    Parameters

    • vectors: number[][]

      Vectors to add.

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

      Documents associated with the vectors.

    Returns Promise<void>

asRetriever

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

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

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

      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: Partial<MultiSearchRequestSchema>

      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<Typesense>

    • 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>

  • Deletes documents from the vector store based on the specified parameters.

    Parameters

    • Optional_params: Record<string, any>

      Flexible key-value pairs defining conditions for document deletion.

    Returns Promise<void>

    A promise that resolves once the deletion is complete.

deleteDocuments

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<Partial<MultiSearchRequestSchema>>
    • _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: Partial<MultiSearchRequestSchema>

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

  • Search for similar documents with their similarity score.

    Parameters

    • vectorPrompt: number[]

      vector to search for

    • Optionalk: number

      amount of results to return

    • filter: Partial<MultiSearchRequestSchema> = {}

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

    similar documents with their similarity score

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: Partial<MultiSearchRequestSchema>

      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, config): Promise<Typesense>

  • Create a vector store from documents.

    Parameters

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

      documents

    • embeddings: EmbeddingsInterface

      embeddings

    • config: TypesenseConfig

      Typesense configuration

    Returns Promise<Typesense>

    Typesense vector store

    Warning

    You can omit this method, and only use the constructor and addDocuments.

StaticfromTexts

Settings

Member Visibility

On This Page

Constructors
Properties
Methods