Documents
Uploads a CSV or Excel sheet into a tabular knowledge base and queues it for ingestion, so an agent can look up rows during a call. Send multipart/form-data with knowledge_base_id and file (up to 2 MB and 10,000 rows). Optionally add sheet_desc to tell the agent what the columns mean, and searchable_columns as a JSON array of the column names it may search by. Poll GET /api/ext/document/{document_id} until it is ready.
curl --request POST \
--url 'https://api.nabrah.ai/api/ext/document/sheet' \
--header 'X-API-Key: <your-api-key>'{
"id": "00000000-0000-4000-8000-000000000000",
"knowledge_base_id": "00000000-0000-4000-8000-000000000000",
"type": "file",
"status": "unknown",
"title": "string",
"summary": "string",
"filename": "string",
"created_at": "2026-01-15T12:00:00.000Z",
"updated_at": "2026-01-15T12:00:00.000Z",
"source_format": "pdf",
"tabular_schema": {},
"sheet_desc": "string",
"searchable_columns": [
"string"
]
}X-API-KeystringheaderrequiredYour workspace API key. Create one in the dashboard under API keys.
Successful Response
application/json
Validation Error
application/json