@promptbook/remote-server
Version:
Promptbook: Create persistent AI agents that turn your company's scattered knowledge into action
38 lines (37 loc) • 1.86 kB
TypeScript
import type { KnowledgePiecePreparedJson } from '../../pipeline/PipelineJson/KnowledgePieceJson';
import type { ExecutionTools } from '../../execution/ExecutionTools';
import type { PrepareAndScrapeOptions } from '../../prepare/PrepareAndScrapeOptions';
import type { Converter } from '../_common/Converter';
import type { ScraperAndConverterMetadata } from '../_common/register/ScraperAndConverterMetadata';
import type { Scraper, ScraperSourceHandler } from '../_common/Scraper';
import type { ScraperIntermediateSource } from '../_common/ScraperIntermediateSource';
/**
* Scraper for old document files (like .doc and .rtf)
*
* @see `documentationUrl` for more details
*
* @public exported from `@promptbook/legacy-documents`
*/
export declare class LegacyDocumentScraper implements Converter, Scraper {
private readonly tools;
private readonly options;
/**
* Metadata of the scraper which includes title, mime types, etc.
*/
get metadata(): ScraperAndConverterMetadata;
/**
* Document scraper is used internally
*/
private readonly documentScraper;
constructor(tools: Pick<ExecutionTools, 'fs' | 'llm' | 'executables'>, options: PrepareAndScrapeOptions);
/**
* Convert the `.doc` or `.rtf` to `.doc` file and returns intermediate source
*
* Note: `$` is used to indicate that this function is not a pure function - it leaves files on the disk and you are responsible for cleaning them by calling `destroy` method of returned object
*/
$convert(source: ScraperSourceHandler): Promise<ScraperIntermediateSource>;
/**
* Scrapes the `.doc` or `.rtf` file and returns the knowledge pieces or `null` if it can't scrape it
*/
scrape(source: ScraperSourceHandler): Promise<ReadonlyArray<Omit<KnowledgePiecePreparedJson, 'sources' | 'preparationIds'>> | null>;
}