langchain.js
    Preparing search index...

    Install and import from @langchain/pinecone instead. Class that extends the VectorStore class and provides methods to interact with the Pinecone vector database.

    Hierarchy (View Summary)

    Index

    Constructors

    • Parameters

      Returns PineconeStore

    Properties

    caller: AsyncCaller
    filter?: PineconeMetadata
    FilterType: PineconeMetadata
    namespace?: string
    pineconeIndex: Index
    textKey: string

    Methods

    • Parameters

      • query: number[]
      • k: number
      • Optionalfilter: PineconeMetadata
      • Optionaloptions: { includeValues: boolean }

      Returns Promise<QueryResponse<RecordMetadata>>

    • Returns string

    • Method that adds documents to the Pinecone database.

      Parameters

      • documents: Document[]

        Array of documents to add to the Pinecone database.

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

        Optional ids for the documents.

      Returns Promise<string[]>

      Promise that resolves with the ids of the added documents.

    • Method that adds vectors to the Pinecone database.

      Parameters

      • vectors: number[][]

        Array of vectors to add to the Pinecone database.

      • documents: Document[]

        Array of documents associated with the vectors.

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

        Optional ids for the vectors.

      Returns Promise<string[]>

      Promise that resolves with the ids of the added vectors.

    • Method that deletes vectors from the Pinecone database.

      Parameters

      Returns Promise<void>

      Promise that resolves when the delete operation is complete.

    • 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<this["FilterType"]>
        • k

          Number of documents to return.

        • fetchK=20

          Number of documents to fetch before passing to the MMR algorithm.

        • lambda=0.5

          Number between 0 and 1 that determines the degree of diversity among the results, where 0 corresponds to maximum diversity and 1 to minimum diversity.

        • filter

          Optional filter to apply to the search.

      Returns Promise<Document[]>

      • List of documents selected by maximal marginal relevance.
    • Method that performs a similarity search in the Pinecone database and returns the results along with their scores.

      Parameters

      • query: number[]

        Query vector for the similarity search.

      • k: number

        Number of top results to return.

      • Optionalfilter: PineconeMetadata

        Optional filter to apply to the search.

      Returns Promise<[Document, number][]>

      Promise that resolves with an array of documents and their scores.

    • Static method that creates a new instance of the PineconeStore class from documents.

      Parameters

      • docs: Document[]

        Array of documents to add to the Pinecone database.

      • embeddings: EmbeddingsInterface

        Embeddings to use for the documents.

      • dbConfig: PineconeLibArgs

        Configuration for the Pinecone database.

      Returns Promise<PineconeStore>

      Promise that resolves with a new instance of the PineconeStore class.

    • Static method that creates a new instance of the PineconeStore class from an existing index.

      Parameters

      • embeddings: EmbeddingsInterface

        Embeddings to use for the documents.

      • dbConfig: PineconeLibArgs

        Configuration for the Pinecone database.

      Returns Promise<PineconeStore>

      Promise that resolves with a new instance of the PineconeStore class.

    • Static method that creates a new instance of the PineconeStore class from texts.

      Parameters

      • texts: string[]

        Array of texts to add to the Pinecone database.

      • metadatas: object | object[]

        Metadata associated with the texts.

      • embeddings: EmbeddingsInterface

        Embeddings to use for the texts.

      • dbConfig: PineconeLibArgs | { namespace?: string; pineconeIndex: Index; textKey?: string }

        Configuration for the Pinecone database.

      Returns Promise<PineconeStore>

      Promise that resolves with a new instance of the PineconeStore class.