/**
 * EmbeddingAgent - Text embedding generation agent
 *
 * Python parity with praisonaiagents/agent/embedding_agent.py
 * Generates embeddings for text using embedding models.
 */
/**
 * Configuration for Embedding settings.
 */
export interface EmbeddingConfig {
    /** Embedding model to use */
    model?: string;
    /** Dimensions for the embedding */
    dimensions?: number;
    /** Batch size for processing multiple texts */
    batchSize?: number;
    /** Timeout in seconds */
    timeout?: number;
}
/**
 * Result of embedding generation.
 */
export interface EmbeddingResult {
    /** The embedding vector */
    embedding: number[];
    /** Model used */
    model: string;
    /** Token usage */
    usage?: {
        promptTokens: number;
        totalTokens: number;
    };
}
/**
 * Result of batch embedding generation.
 */
export interface BatchEmbeddingResult {
    /** Array of embeddings */
    embeddings: number[][];
    /** Model used */
    model: string;
    /** Total token usage */
    usage?: {
        promptTokens: number;
        totalTokens: number;
    };
}
/**
 * Configuration for creating an EmbeddingAgent.
 */
export interface EmbeddingAgentConfig {
    /** Agent name */
    name?: string;
    /** Embedding model */
    llm?: string;
    /** Alias for llm */
    model?: string;
    /** Embedding configuration */
    embedding?: boolean | EmbeddingConfig;
    /** Enable verbose output */
    verbose?: boolean;
}
/**
 * Agent for generating text embeddings.
 *
 * @example
 * ```typescript
 * import { EmbeddingAgent } from 'praisonai';
 *
 * const agent = new EmbeddingAgent({});
 *
 * // Generate embedding for text
 * const result = await agent.embed('Hello, world!');
 * console.log(result.embedding.length); // 1536
 *
 * // Generate embeddings for multiple texts
 * const results = await agent.embedMany(['Hello', 'World']);
 * ```
 */
export declare class EmbeddingAgent {
    static readonly DEFAULT_MODEL = "text-embedding-3-small";
    readonly name: string;
    private readonly model;
    private readonly verbose;
    private readonly embeddingConfig;
    constructor(config: EmbeddingAgentConfig);
    private log;
    /**
     * Generate embedding for a single text.
     *
     * @param text - Text to embed
     * @returns EmbeddingResult with the embedding vector
     */
    embed(text: string): Promise<EmbeddingResult>;
    /**
     * Generate embeddings for multiple texts.
     *
     * @param texts - Array of texts to embed
     * @returns BatchEmbeddingResult with all embeddings
     */
    embedMany(texts: string[]): Promise<BatchEmbeddingResult>;
    /**
     * Calculate cosine similarity between two embeddings.
     */
    cosineSimilarity(a: number[], b: number[]): number;
    /**
     * Find the most similar text from a list.
     */
    findMostSimilar(query: string, candidates: string[]): Promise<{
        text: string;
        similarity: number;
        index: number;
    }>;
}
/**
 * Create an EmbeddingAgent instance.
 */
export declare function createEmbeddingAgent(config: EmbeddingAgentConfig): EmbeddingAgent;