For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Index all files from a specific directory (prefix) in an Azure Blob container.
Headers:
- Authorization: Bearer {api_key} - Captain API key for authentication
- X-Organization-ID: Organization UUID
- Idempotency-Key: UUID for request deduplication (optional)
Args:
collection_name: Name of the collection (path parameter)
body: Azure Blob directory configuration with directory_path
Returns:
{ job_id, status: "pending" }
Path parameters
collection_namestringRequired
Headers
authorizationstringOptional
Request
This endpoint expects an object.
account_keystringRequired
account_namestringRequired
container_namestringRequired
directory_pathstringRequired
Path to the directory within the container. Accepts either a relative path (e.g., 'reports/2024/january') or a full Azure Blob URI (e.g., 'https://account.blob.core.windows.net/container/reports/2024/january'). All blobs within this prefix will be indexed.
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.
Allowed values:
custom_metadatamap from strings to optional strings or integers or doubles or booleans or lists of stringsOptional
Custom metadata to attach to all indexed chunks. Keys must be strings. Values: str, int, float, bool, or List[str].
max_filesintegerOptional
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_scriptstringOptional
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.
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.
Response
Successful Response
job_idstring
statusstringDefaults to pending
Errors
400
Index Azure Directory V2request Bad Request Error
Index all files from a specific directory (prefix) in an Azure Blob container.
Headers:
Authorization: Bearer {api_key} - Captain API key for authentication
X-Organization-ID: Organization UUID
Idempotency-Key: UUID for request deduplication (optional)
Args:
collection_name: Name of the collection (path parameter)
body: Azure Blob directory configuration with directory_path
