import type { ImageType } from "../Node.js";
import type { VectorStoreQueryMode } from "../storage/vectorStore/types.js";
/**
 * Similarity type
 * Default is cosine similarity. Dot product and negative Euclidean distance are also supported.
 */
export declare enum SimilarityType {
    DEFAULT = "cosine",
    DOT_PRODUCT = "dot_product",
    EUCLIDEAN = "euclidean"
}
/**
 * The similarity between two embeddings.
 * @param embedding1
 * @param embedding2
 * @param mode
 * @returns similarity score with higher numbers meaning the two embeddings are more similar
 */
export declare function similarity(embedding1: number[], embedding2: number[], mode?: SimilarityType): number;
/**
 * Get the top K embeddings from a list of embeddings ordered by similarity to the query.
 * @param queryEmbedding
 * @param embeddings list of embeddings to consider
 * @param similarityTopK max number of embeddings to return, default 2
 * @param embeddingIds ids of embeddings in the embeddings list
 * @param similarityCutoff minimum similarity score
 * @returns
 */
export declare function getTopKEmbeddings(queryEmbedding: number[], embeddings: number[][], similarityTopK?: number, embeddingIds?: any[] | null, similarityCutoff?: number | null): [number[], any[]];
export declare function getTopKEmbeddingsLearner(queryEmbedding: number[], embeddings: number[][], similarityTopK?: number, embeddingsIds?: any[], queryMode?: VectorStoreQueryMode): [number[], any[]];
export declare function getTopKMMREmbeddings(queryEmbedding: number[], embeddings: number[][], similarityFn?: ((...args: any[]) => number) | null, similarityTopK?: number | null, embeddingIds?: any[] | null, _similarityCutoff?: number | null, mmrThreshold?: number | null): [number[], any[]];
export declare function imageToString(input: ImageType): Promise<string>;
export declare function stringToImage(input: string): ImageType;
export declare function imageToDataUrl(input: ImageType): Promise<string>;