Index File Upload | Captain Docs

Upload and index files directly into a collection via multipart form-data.

Upload one or more files (max 20) in a single request. Supports PDF, DOCX, XLSX, CSV, TXT, images, and other document types. Files are processed through the same pipeline as cloud storage indexing.

Supported File Types

PDF, DOCX, DOC, XLSX, XLS, CSV, TSV, TXT, MD, JSON, YAML, YML, PNG, JPG, JPEG, GIF, BMP, TIFF

Size Limits

Maximum 100MB per file
Maximum 20 files per request

Processing Modes

advanced: AI-enhanced extraction for complex layouts, tables, figures, charts, and documents containing images (2.5 credits/page)
basic: Standard document processing optimized for general indexing (1 credit/page)

Returns a job_id for tracking progress via GET /v2/jobs/{job_id}.

Upload and index files directly into a collection via multipart form-data. Upload one or more files (max 20) in a single request. Supports PDF, DOCX, XLSX, CSV, TXT, images, and other document types. Files are processed through the same pipeline as cloud storage indexing. ## Supported File Types PDF, DOCX, DOC, XLSX, XLS, CSV, TSV, TXT, MD, JSON, YAML, YML, PNG, JPG, JPEG, GIF, BMP, TIFF ## Size Limits - Maximum 100MB per file - Maximum 20 files per request ## Processing Modes - **advanced**: AI-enhanced extraction for complex layouts, tables, figures, charts, and documents containing images (2.5 credits/page) - **basic**: Standard document processing optimized for general indexing (1 credit/page) Returns a job_id for tracking progress via GET /v2/jobs/{job_id}.

Authentication

AuthorizationBearer

Bearer token authentication using API key

Path parameters

collection_namestringRequired

Name of the collection to index into

Request

This endpoint expects a multipart form with multiple files.

filesfilesRequired

One or more files to upload and index (max 20)

processing_typeenumOptionalDefaults to basic

Document processing type: ‘advanced’ for AI-enhanced extraction, ‘basic’ for standard processing

Allowed values:

custom_metadatastringOptional

JSON string of custom metadata to attach to all indexed chunks

Response

Indexing job started

job_idstring

statusenum

Allowed values:

Upload and index files directly into a collection via multipart form-data.

Upload one or more files (max 20) in a single request. Supports PDF, DOCX, XLSX, CSV, TXT, images, and other document types. Files are processed through the same pipeline as cloud storage indexing.

Supported File Types

PDF, DOCX, DOC, XLSX, XLS, CSV, TSV, TXT, MD, JSON, YAML, YML, PNG, JPG, JPEG, GIF, BMP, TIFF

Size Limits

Maximum 100MB per file
Maximum 20 files per request

Processing Modes

advanced: AI-enhanced extraction for complex layouts, tables, figures, charts, and documents containing images (2.5 credits/page)
basic: Standard document processing optimized for general indexing (1 credit/page)

Returns a job_id for tracking progress via GET /v2/jobs/{job_id}.

1	import requests
2
3	BASE_URL = "https://api.runcaptain.com"
4	API_KEY = "your_api_key"
5	ORG_ID = "your_organization_id"
6
7	headers = {
8	"Authorization": f"Bearer {API_KEY}",
9	"X-Organization-ID": ORG_ID
10	}
11
12	with open("report.pdf", "rb") as f:
13	response = requests.post(
14	f"{BASE_URL}/v2/collections/my_collection/index/file",
15	headers=headers,
16	files=[("files", ("report.pdf", f, "application/pdf"))],
17	data={"processing_type": "advanced"},
18	timeout=120.0
19	)
20
21	if response.status_code in [200, 201]:
22	data = response.json()
23	print(f"Job started! ID: {data['job_id']}")
24	else:
25	print(f"Error: {response.status_code}")

1	{
2	"job_id": "abc123xyz-1234567890",
3	"status": "pending"
4	}

Supported File Types

Size Limits

Processing Modes

Authentication

Path parameters

Headers

Request

Response

Supported File Types

Size Limits

Processing Modes