@juspay/neurolink/dist/rag/document/loaders.d.ts

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

/**
 * Document Loaders
 *
 * Provides loaders for various document formats including:
 * - Text files
 * - Markdown files
 * - HTML files and web pages
 * - JSON files
 * - CSV files
 * - PDF files
 *
 * @example
 * ```typescript
 * import { loadDocument, WebLoader, PDFLoader } from 'neurolink/rag';
 *
 * // Load from file path
 * const doc = await loadDocument('/path/to/document.md');
 *
 * // Load from URL
 * const webDoc = await WebLoader.load('https://example.com/article');
 *
 * // Load PDF
 * const pdfDoc = await PDFLoader.load('/path/to/document.pdf');
 * ```
 */
import type { LoaderOptions, WebLoaderOptions, PDFLoaderOptions, CSVLoaderOptions, DocumentLoader } from "../../types/index.js";
import { MDocument } from "./MDocument.js";
/**
 * Text file loader
 */
export declare class TextLoader implements DocumentLoader {
    load(source: string, options?: LoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
    protected loadContent(source: string, encoding?: BufferEncoding): Promise<string>;
    protected getSourceName(source: string): string;
}
/**
 * Markdown file loader
 */
export declare class MarkdownLoader extends TextLoader {
    load(source: string, options?: LoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
}
/**
 * HTML file loader
 */
export declare class HTMLLoader extends TextLoader {
    load(source: string, options?: LoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
}
/**
 * JSON file loader
 */
export declare class JSONLoader extends TextLoader {
    load(source: string, options?: LoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
}
/**
 * CSV file loader
 */
export declare class CSVLoader extends TextLoader {
    load(source: string, options?: CSVLoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
    private toMarkdownTable;
    private toTextTable;
    /**
     * Collapse embedded newlines to a single space so one logical CSV row
     * renders as exactly one line in the text/markdown table output.
     *
     * The shared quote-aware parser (`splitCsvLines` + `splitCSVFields`)
     * preserves newlines embedded inside a quoted field verbatim — correct
     * for the `json` output format (where `JSON.stringify` escapes them), but
     * left as-is here it would split a single record across multiple
     * physical table rows. Mirrors the same normalization `CSVProcessor`
     * already applies in its own markdown formatter.
     */
    private collapseEmbeddedNewlines;
}
/**
 * PDF file loader
 *
 * Note: Requires external PDF processing library for full functionality.
 * Falls back to placeholder implementation if pdf-parse is not available.
 */
export declare class PDFLoader implements DocumentLoader {
    load(source: string, options?: PDFLoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
    private loadPdfParser;
    private parsePageRange;
}
/**
 * Web page loader
 *
 * Fetches and extracts content from web pages.
 * Supports basic HTML parsing without external dependencies.
 */
export declare class WebLoader implements DocumentLoader {
    private defaultUserAgent;
    load(source: string, options?: WebLoaderOptions): Promise<MDocument>;
    canHandle(source: string): boolean;
    /**
     * Extract main content from HTML
     */
    private extractMainContent;
    /**
     * Convert HTML to plain text
     */
    private htmlToText;
}
/**
 * Load document from file path, URL, or content
 *
 * Automatically detects the document type and uses the appropriate loader.
 *
 * @param source - File path, URL, or raw content
 * @param options - Loader options
 * @returns Promise resolving to MDocument
 *
 * @example
 * ```typescript
 * // Load from file
 * const doc = await loadDocument('/path/to/document.md');
 *
 * // Load from URL
 * const webDoc = await loadDocument('https://example.com/article');
 *
 * // Load with options
 * const pdfDoc = await loadDocument('/path/to/doc.pdf', {
 *   pageRange: '1-5',
 *   metadata: { project: 'research' }
 * });
 * ```
 */
export declare function loadDocument(source: string, options?: LoaderOptions): Promise<MDocument>;
/**
 * Load multiple documents
 *
 * @param sources - Array of file paths, URLs, or content
 * @param options - Loader options (applied to all)
 * @returns Promise resolving to array of MDocuments
 */
export declare function loadDocuments(sources: string[], options?: LoaderOptions): Promise<MDocument[]>;