UNPKG

@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
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>; }