v44

latestOpenAPI 3.1.0Proprietaryraw.githubusercontent.com2026-05-192301780.0 KB

Vaults

Ingest vault object

Triggers ingestion workflow for a vault object to extract text, generate chunks, and create embeddings. For supported file types (PDF, DOCX, PPTX, TXT, RTF, XML, HTML, Markdown, CSV/TSV, JSON/YAML/TOML, common source code files, ZIP, audio, video), processing happens asynchronously. ZIP archives are unpacked recursively up to 5 levels, and each extracted file is created as an independent vault object and ingested via the normal pipeline. For unsupported types (images, etc.), the file is marked as completed immediately without text extraction. GraphRAG indexing must be triggered separately via POST /vault/:id/graphrag/:objectId.

post/vault/{id}/ingest/{objectId}

Path parameters

idstring required

Vault ID

objectIdstring required

Vault object ID

Response

Ingestion workflow started successfully

objectIdstring required

ID of the vault object being processed

workflowIdstring nullable required

Workflow run ID for tracking progress. Null for file types that skip processing.

status'processing' | 'stored' required

Current ingestion status. 'stored' for file types without text extraction (no chunks/vectors created).

messagestring required

Human-readable status message

enableGraphRAGboolean required

Always false - GraphRAG must be triggered separately via POST /vault/:id/graphrag/:objectId