@karmaniverous/jeeves-watcher
    Preparing search index...

    Class VectorStoreClient

    Client wrapper for Qdrant vector store operations.

    Implements the VectorStore interface for dependency inversion.

    Implements

    Index

    Constructors

    • Create a new VectorStoreClient.

      Parameters

      • config: { apiKey?: string; collectionName: string; url: string }

        Vector store configuration.

        • OptionalapiKey?: string

          Qdrant API key.

        • collectionName: string

          Qdrant collection name.

        • url: string

          Qdrant server URL.

      • dimensions: number

        The embedding vector dimensions.

      • Optionallogger: Logger<never, boolean>

        Optional pino logger for retry warnings.

      Returns VectorStoreClient

    Methods

    • Hybrid search combining dense vector and full-text match with RRF fusion.

      Parameters

      • vector: number[]

        The query vector.

      • queryText: string

        The raw query text for full-text matching.

      • limit: number

        Maximum results to return.

      • textWeight: number

        Weight for text results in RRF (0–1).

      • Optionalfilter: Record<string, unknown>

        Optional Qdrant filter.

      Returns Promise<SearchResult[]>

      An array of search results.