@promptbook/vercel
Version:
Promptbook: Turn your company's scattered knowledge into AI ready books
42 lines (41 loc) • 1.97 kB
TypeScript
import type { KnowledgePiecePreparedJson } from '../../pipeline/PipelineJson/KnowledgePieceJson';
import type { Scraper } from '../_common/Scraper';
import type { ScraperSourceHandler } from '../_common/Scraper';
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 { ScraperIntermediateSource } from '../_common/ScraperIntermediateSource';
/**
* Scraper for .pdf files
*
* @see `documentationUrl` for more details
* @public exported from `@promptbook/pdf`
*/
export declare class PdfScraper implements Converter, Scraper {
private readonly tools;
private readonly options;
/**
* Metadata of the scraper which includes title, mime types, etc.
*/
get metadata(): ScraperAndConverterMetadata;
/**
* Markdown scraper is used internally
*/
private readonly markdownScraper;
constructor(tools: Pick<ExecutionTools, 'llm'>, options: PrepareAndScrapeOptions);
/**
* Converts the `.pdf` file to `.md` file and returns intermediate source
*/
$convert(source: ScraperSourceHandler): Promise<ScraperIntermediateSource>;
/**
* Scrapes the `.pdf` file and returns the knowledge pieces or `null` if it can't scrape it
*/
scrape(source: ScraperSourceHandler): Promise<ReadonlyArray<Omit<KnowledgePiecePreparedJson, 'sources' | 'preparationIds'>> | null>;
}
/**
* TODO: [👣] Converted pdf documents can act as cached items - there is no need to run conversion each time
* TODO: [🪂] Do it in parallel 11:11
* Note: No need to aggregate usage here, it is done by intercepting the llmTools
* Note: [🟢] Code in this file should never be never released in packages that could be imported into browser environment
*/