Index Dropbox Directory

Path to a folder within the Dropbox account (e.g. '/Reports/2024'). All files within this folder and its subfolders are indexed recursively.

Dropbox access token with files.metadata.read and files.content.read scopes. Generate one from the Dropbox App Console (Settings tab -> Generated access token). Tokens are short-lived and scoped to the token owner's account, ideal for one-shot indexing jobs.

When true, files that already exist in the collection are re-indexed and replaced with zero downtime: the new version is built alongside the live one and atomically swapped in when complete, so the previous version keeps serving search results throughout the rebuild. The document keeps the same document_id across overwrites, and its status reads 'updating' in the document listing while the rebuild runs. Requires skip_existing=false. Setting both to true returns a 400 error.

Relative path to a JS parsing script for JSON files (e.g. 'research/paper-parser'). When provided, .json files are processed through a sandboxed V8 isolate. Without this, .json files are indexed as raw text.

Document processing type. 'advanced' uses agentic OCR with AI-enhanced extraction for complex layouts, tables, figures, charts, and documents containing images. 'basic' provides reliable OCR optimized for general document indexing and high-volume processing.

When true, files already indexed in the collection are skipped and will not be re-indexed with incoming changes. When false, all incoming files are indexed regardless of whether they already exist.

When true, detected PII (emails, phone numbers, SSNs, credit cards, names, and locations) is masked in the parsed content before it is embedded and stored — replaced with entity tags like <PERSON> and <EMAIL_ADDRESS>. For images (including images embedded in PDFs), PII text visible in the image is also pixel-redacted. Opt-in; defaults to false, which leaves content unchanged.

Masking engine for this job. kev (default): the Kev classifier model on Captain's infrastructure; supports pii_fields and pii_instructions; no fallback, so a file kev cannot mask fails to index and the rest of the job continues. jev: TypeSafe's hosted Jev model, slightly more accurate, best-effort availability; supports custom fields and instructions and may list fallbacks in pii_fallback. presidio: the legacy pattern engine, built-in categories only (rejects pii_fields or pii_instructions with 422), never a fallback. Requires mask_pii: true. The earlier names captain-jev and captain-presidio keep working as before; new requests should use kev, jev or presidio.

Plain-language guidance that steers what counts as personal data for this job, for the built-in categories and any pii_fields. For example: 'Names of hospital staff may stay; patient names, record numbers and bed assignments must be masked.' Requires mask_pii to be true. Up to 1,000 characters.

AWS Transcribe language code for the spoken audio (e.g. 'es-US', 'pt-BR'). Omit to auto-detect per file. Video and audio files only. Supported codes: https://docs.aws.amazon.com/transcribe/latest/dg/supported-languages.html