nodes/generated

Interface VectorStoreInMemoryNodeParameters

Source


interface VectorStoreInMemoryNodeParameters {
    clearStore?: boolean;
    embeddingBatchSize?: number;
    id?: string;
    includeDocumentMetadata?: boolean;
    memoryKey?:
        | string
        | { mode: "id"
        | "list"; value: string };
    mode?:
        | "load"
        | "insert"
        | "retrieve"
        | "retrieve-as-tool";
    prompt?: string;
    toolDescription?: string;
    toolName?: string;
    topK?: number;
    useReranker?: boolean;
}

Properties§

§readonly clearStore?: boolean

Whether to clear the store before inserting new data

§readonly embeddingBatchSize?: number

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

§readonly id?: string

ID of an embedding entry

§readonly includeDocumentMetadata?: boolean

Whether or not to include document metadata Default: true

§readonly memoryKey?: string | { mode: "id" | "list"; value: string }

The key to use to store the vector memory in the workflow data. The key will be prefixed with the workflow ID to avoid collisions. Default: "vector_store_key"

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

Default: "retrieve"

§readonly prompt?: string

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

§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}

§readonly toolName?: string

Name of the vector store

§readonly topK?: number

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

§readonly useReranker?: boolean

Whether or not to rerank results