import type { CrawlerPatternTypeEnum } from './CrawlerPatternTypeEnum'; export type TrainDocumentViewRequest = { /** * Pathway for document to be trained in */ pathway?: string; /** * Url of the document to be trained */ url?: string; /** * Search text for wikipedia */ text?: string; /** * Type of document e.g file */ type: string; /** * If file should be translated */ translate?: boolean; /** * File to be trained */ file?: Blob; /** * Accessibilityto the file */ access?: string; /** * Branch of the repository */ branch?: string; /** * Authentication and scoped details of google drive */ google_drive_auth_data?: any; /** * Authentication and scoped details of dropbox */ dropbox_auth_data?: any; /** * The max depth of the crawler */ crawler_max_depth?: number; /** * The max pages limit of the crawler */ crawler_max_pages_limit?: number; /** * The max concurrency of the crawler */ crawler_max_concurrency?: number; /** * The patterns that the crawler should use to match urls. Patterns may be a glob pattern or a full regex pattern. Indicate the specified type in `crawler_pattern_type`. */ crawler_match_patterns?: Array; /** * Pattern type for the crawler * * * `glob` - Glob * * `regex` - Regex */ crawler_pattern_type?: CrawlerPatternTypeEnum; /** * Extra HTTP headers the crawler sends on every request, as a flat object of string header names to string values. */ crawler_extra_headers?: Record; /** * Custom metadata to attach to the trained document. Must be a flat JSON object with string keys and string, number, or boolean values. */ custom_metadata?: any; /** * Adds document to the pool or not. */ add_to_document_pool?: boolean; /** * Only adds document to document pool. Requires pathway to be empty. */ document_pool_only?: boolean; /** * Description of an image submitted by the user for RAG. */ user_image_description?: string; /** * GitHub access token with repo scope. Required for private repositories. */ github_access_token?: string; };