Class Milvus

constructor

• new Milvus(embeddings: EmbeddingsInterface, args: MilvusLibArgs): Milvus

  Parameters

  • embeddings: EmbeddingsInterface
  • args: MilvusLibArgs

  Returns Milvus

OptionalautoId

client

collectionName

embeddings

fields

FilterType

indexCreateParams

indexSearchParams

OptionalnumDimensions

OptionalpartitionKey

OptionalpartitionKeyMaxLength

OptionalpartitionName

primaryField

textField

textFieldMaxLength

vectorField

lc_secrets

• get lc_secrets(): { [key: string]: string }

  Returns { [key: string]: string }

_vectorstoreType

• _vectorstoreType(): string

  Returns string

addDocuments

• addDocuments(documents: Document[], options?: { ids?: string[] }): Promise<void>

  Adds documents to the Milvus database.

  Parameters

  • documents: Document[]

    Array of Document instances to be added to the database.

  • Optionaloptions: { ids?: string[] }

    Optional parameter that can include specific IDs for the documents.

  Returns Promise<void>

  Promise resolving to void.

addVectors

• addVectors(
      vectors: number[][],
      documents: Document[],
      options?: { ids?: string[] },
  ): Promise<void>

  Adds vectors to the Milvus database.

  Parameters

  • vectors: number[][]

    Array of vectors to be added to the database.

  • documents: Document[]

    Array of Document instances associated with the vectors.

  • Optionaloptions: { ids?: string[] }

    Optional parameter that can include specific IDs for the documents.

  Returns Promise<void>

  Promise resolving to void.

createCollection

• createCollection(vectors: number[][], documents: Document[]): Promise<void>

  Creates a collection in the Milvus database.

  Parameters

  • vectors: number[][]

    Array of vectors to be added to the new collection.

  • documents: Document[]

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

  Returns Promise<void>

  Promise resolving to void.

delete

• delete(params: { filter?: string; ids?: string[] }): Promise<void>

  Deletes data from the Milvus database.

  Parameters

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

    Object containing a filter to apply to the deletion.

  Returns Promise<void>

  Promise resolving to void.

ensureCollection

• ensureCollection(vectors?: number[][], documents?: Document[]): 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[]

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

  Returns Promise<void>

  Promise resolving to void.

ensurePartition

• ensurePartition(): Promise<void>

  Ensures that a partition exists in the Milvus collection.

  Returns Promise<void>

  Promise resolving to void.

grabCollectionFields

• grabCollectionFields(): Promise<void>

  Retrieves the fields of a collection in the Milvus database.

  Returns Promise<void>

  Promise resolving to void.

similaritySearchVectorWithScore

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

  Promise resolving to an array of tuples, each containing a Document instance and a similarity score.

StaticfromDocuments

• fromDocuments(
      docs: Document[],
      embeddings: EmbeddingsInterface,
      dbConfig?: MilvusLibArgs,
  ): Promise<Milvus>

  Creates a Milvus instance from a set of Document instances.

  Parameters

  • docs: Document[]

    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: EmbeddingsInterface,
      dbConfig: MilvusLibArgs,
  ): 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: string[],
      metadatas: object | object[],
      embeddings: EmbeddingsInterface,
      dbConfig?: MilvusLibArgs,
  ): 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.