@n8n/n8n-nodes-langchain/dist/node-definitions/nodes/n8n-nodes-langchain/vectorStoreInMemory/v1/mode_insert.ts

/**
 * Simple Vector Store Node - Version 1
 * Discriminator: mode=insert
 */


/** Insert documents into vector store */
export type LcVectorStoreInMemoryV1InsertParams = {
  /**
   * Sits on the main flow — pipe the documents you want to embed into this node. Declare with `vectorStore({...})`. Required subnodes: `embedding` and `documentLoader`. If the goal is letting an LLM query the store, use `mode: 'retrieve-as-tool'` instead.
   * <patterns>
   * <pattern title="insert mode — upsert documents (generic, works for any vectorStore* node)">
   * // Substitute the type literal and provider-specific parameters (e.g. pineconeIndex,
   * // qdrantCollection, supabaseTableName) — see the rest of this file for the exact shape.
   * const store = vectorStore({
   *   type: '@n8n/n8n-nodes-langchain.vectorStoreXxx',
   *   config: {
   *     name: 'Knowledge Base',
   *     parameters: {
   *       mode: 'insert',
   *       // ...provider-specific parameters
   *     },
   *     subnodes: { embedding: embeddingsOpenAi, documentLoader: defaultDataLoader }
   *   }
   * });
   * </pattern>
   * </patterns>
   */
  mode: 'insert';
/**
 * 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
 */
    memoryKey?: string | Expression<string>;
/**
 * Whether to clear the store before inserting new data
 * @default false
 */
    clearStore?: boolean | Expression<boolean>;
};

export interface LcVectorStoreInMemoryV1InsertSubnodeConfig {
  embedding: EmbeddingInstance | EmbeddingInstance[];
  documentLoader: DocumentLoaderInstance | DocumentLoaderInstance[];
}

export type LcVectorStoreInMemoryV1InsertNode = {
  type: '@n8n/n8n-nodes-langchain.vectorStoreInMemory';
  version: 1;
  config: NodeConfig<LcVectorStoreInMemoryV1InsertParams> & { subnodes: LcVectorStoreInMemoryV1InsertSubnodeConfig };
};