Class Milvus

Class for interacting with a Milvus database. Extends the VectorStore class.

Hierarchy

  • VectorStore
    • Milvus

Constructors

constructor

Properties

FilterType autoId? client collectionName embeddings fields indexCreateParams indexSearchParams numDimensions? partitionKey? partitionKeyMaxLength? partitionName? primaryField textField textFieldMaxLength vectorField

Methods

addDocuments addVectors asRetriever createCollection delete ensureCollection ensurePartition grabCollectionFields maxMarginalRelevanceSearch? similaritySearch similaritySearchVectorWithScore similaritySearchWithScore toJSON toJSONNotImplemented fromDocuments fromExistingCollection fromTexts

Constructors

constructor

Properties

FilterType

FilterType: string

OptionalautoId

autoId?: boolean

client

client: MilvusClient

collectionName

collectionName: string

embeddings

embeddings: EmbeddingsInterface

fields

fields: string[]

indexCreateParams

indexCreateParams: IndexCreateOptions

indexSearchParams

indexSearchParams: keyValueObj

OptionalnumDimensions

numDimensions?: number

OptionalpartitionKey

partitionKey?: string

OptionalpartitionKeyMaxLength

partitionKeyMaxLength?: number

OptionalpartitionName

partitionName?: string

primaryField

primaryField: string

textField

textField: string

textFieldMaxLength

textFieldMaxLength: number

vectorField

vectorField: string

Methods

addDocuments

  • addDocuments(documents, options?): Promise<void>

  • Adds documents to the Milvus database.

    Parameters

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

      Array of Document instances to be added to the database.

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

      Optional parameter that can include specific IDs for the documents.

      • Optionalids?: string[]

    Returns Promise<void>

    Promise resolving to void.

addVectors

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

  • Adds vectors to the Milvus database.

    Parameters

    • vectors: number[][]

      Array of vectors to be added to the database.

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

      Array of Document instances associated with the vectors.

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

      Optional parameter that can include specific IDs for the documents.

      • Optionalids?: string[]

    Returns Promise<void>

    Promise resolving to void.

asRetriever

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

  • Creates a VectorStoreRetriever instance with flexible configuration options.

    Parameters

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

      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<Milvus>

    • 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 },
    });

createCollection

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

  • Creates a collection in the Milvus database.

    Parameters

    • vectors: number[][]

      Array of vectors to be added to the new collection.

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

      Array of Document instances to be added to the new collection.

    Returns Promise<void>

    Promise resolving to void.

delete

  • delete(params): Promise<void>

  • Deletes data from the Milvus database.

    Parameters

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

      Object containing a filter to apply to the deletion.

      • Optionalfilter?: string
      • Optionalids?: string[]

    Returns Promise<void>

    Promise resolving to void.

ensureCollection

  • ensureCollection(vectors?, documents?): Promise<void>

  • Ensures that a collection exists in the Milvus database.

    Parameters

    • Optionalvectors: number[][]

      Optional array of vectors to be used if a new collection needs to be created.

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

      Optional array of Document instances to be used if a new collection needs to be created.

    Returns Promise<void>

    Promise resolving to void.

ensurePartition

grabCollectionFields

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][]>

  • Searches for vectors in the Milvus database that are similar to a given vector.

    Parameters

    • query: number[]

      Vector to compare with the vectors in the database.

    • k: number

      Number of similar vectors to return.

    • Optionalfilter: string

      Optional filter to apply to the search.

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

    Promise resolving to an array of tuples, each containing a Document instance and a 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: 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<Milvus>

  • Creates a Milvus instance from a set of Document instances.

    Parameters

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

      Array of Document instances to be added to the database.

    • embeddings: EmbeddingsInterface

      Embeddings instance used to generate vector embeddings for the documents.

    • OptionaldbConfig: MilvusLibArgs

      Optional configuration for the Milvus database.

    Returns Promise<Milvus>

    Promise resolving to a new Milvus instance.

StaticfromExistingCollection

  • fromExistingCollection(embeddings, dbConfig): Promise<Milvus>

  • Creates a Milvus instance from an existing collection in the Milvus database.

    Parameters

    • embeddings: EmbeddingsInterface

      Embeddings instance used to generate vector embeddings for the documents in the collection.

    • dbConfig: MilvusLibArgs

      Configuration for the Milvus database.

    Returns Promise<Milvus>

    Promise resolving to a new Milvus instance.

StaticfromTexts

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

  • Creates a Milvus instance from a set of texts and their associated metadata.

    Parameters

    • texts: string[]

      Array of texts to be added to the database.

    • metadatas: object | object[]

      Array of metadata objects associated with the texts.

    • embeddings: EmbeddingsInterface

      Embeddings instance used to generate vector embeddings for the texts.

    • OptionaldbConfig: MilvusLibArgs

      Optional configuration for the Milvus database.

    Returns Promise<Milvus>

    Promise resolving to a new Milvus instance.

Settings

Member Visibility

On This Page

Constructors
Properties
Methods