nodes/generated

Interface VectorStoreZepNodeParameters

Source
interface VectorStoreZepNodeParameters {
    collectionName?: string;
    embeddingBatchSize?: number;
    id?: string;
    includeDocumentMetadata?: boolean;
    mode?:
        | "load"
        | "insert"
        | "retrieve"
        | "retrieve-as-tool";
    options?: | {
        embeddingDimensions?: number;
        isAutoEmbedded?: boolean;
    }
    | {
        embeddingDimensions?: number;
        metadata?: {
            metadataValues: { name: string; value?: string }[];
        };
    };
    prompt?: string;
    toolDescription?: string;
    toolName?: string;
    topK?: number;
    useReranker?: boolean;
}

Properties§

Source§

readonly collectionName?: string

Source§

readonly embeddingBatchSize?: number

Number of documents to embed in a single batch Default: 200

Source§

readonly id?: string

ID of an embedding entry

Source§

readonly includeDocumentMetadata?: boolean

Whether or not to include document metadata Default: true

Source§

readonly mode?: "load" | "insert" | "retrieve" | "retrieve-as-tool"

Default: "retrieve"

Source§

readonly options?:
    | {
        embeddingDimensions?: number;
        isAutoEmbedded?: boolean;
    }
    | {
        embeddingDimensions?: number;
        metadata?: {
            metadataValues: { name: string; value?: string }[];
        };
    }

Default: {}

Source§

readonly prompt?: string

Search prompt to retrieve matching documents from the vector store using similarity-based ranking

Source§

readonly toolDescription?: string

Explain to the LLM what this tool does, a good, specific description would allow LLMs to produce expected results much more often Type options: {"rows":2}

Source§

readonly toolName?: string

Name of the vector store

Source§

readonly topK?: number

Number of top results to fetch from vector store Default: 4

Source§

readonly useReranker?: boolean

Whether or not to rerank results