Index Backblaze File

Index a single file from a Backblaze B2 bucket into a collection. Headers: - Authorization: Bearer {api_key} - Captain API key for authentication - X-Organization-ID: Organization UUID Args: collection_name: Name of the collection (path parameter) body: Backblaze file configuration with file_uri (object key within the bucket, e.g. reports/annual-review.pdf) Returns: { job_id, status: "pending" }

Path parameters

collection_namestringRequired

Headers

authorizationstring or nullOptional

Request

This endpoint expects an object.
access_key_idstringRequired

Backblaze B2 Application Key ID (used as the S3 access key ID). Create one on the App Keys page — the master application key cannot be used with the S3-compatible API.

bucket_namestringRequired
endpoint_urlstringRequired

S3-compatible endpoint URL for your Backblaze B2 bucket, in the form https://s3.<region>.backblazeb2.com (e.g. https://s3.us-west-004.backblazeb2.com). Required.

file_uristringRequired

Object key within the bucket, e.g. ‘reports/annual-review.pdf’. A full s3://bucket/key URI is also accepted.

processing_typeenumRequired

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.

secret_access_keystringRequired

Backblaze B2 Application Key (used as the S3 secret access key; shown once when the key is created).

custom_metadatamap from strings to strings or integers or doubles or booleans or lists of strings or nullOptional

Custom metadata to attach to all chunks from this file. Keys must be strings. Values: str, int, float, bool, or List[str].

overwrite_existingbooleanOptionalDefaults to false

When true, files that already exist in the collection will be deleted and re-indexed with the latest changes. Requires skip_existing=false. Setting both to true returns a 400 error.

parsing_scriptstring or nullOptional

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.

regionstringOptionalDefaults to us-east-1

Region of your Backblaze B2 bucket (e.g. ‘us-west-004’), matching the endpoint URL. Required by the S3 protocol; defaults to ‘us-east-1’.

skip_existingbooleanOptionalDefaults to true

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.

transcription_languagestring or nullOptional

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

Response

Successful Response
job_idstring
statusstringDefaults to pending

Errors

400
Bad Request Error