What authentication does the Papra API use?

The Papra API uses bearer token authentication. Through Jentic, the token is stored in the encrypted vault and injected at execution time so it never enters the agent's prompt context.

How does OCR work when uploading documents?

POST /api/organizations/{organizationId}/documents accepts a file via multipart/form-data with an optional ocrLanguages parameter to specify the language(s) for text extraction. The API automatically processes the document and extracts searchable text content.

Can I search document content?

Yes. GET /api/organizations/{organizationId}/documents/search accepts a searchQuery parameter and returns all documents matching the full-text search with pagination support. The search covers OCR-extracted text and document metadata.

How do automated tagging rules work?

POST /api/organizations/{organizationId}/tagging-rules/{taggingRuleId}/apply triggers an automated tagging task that applies predefined rules to documents. The endpoint returns a taskId for tracking the async operation.

Can I track document changes?

Yes. GET /api/organizations/{organizationId}/documents/{documentId}/activity returns a paginated activity log with timestamps and event types including uploads, edits, tag assignments, and views. Essential for compliance and audit trails.

Can I limit what my agent is allowed to do with the Papra API?

Yes. Because Papra puts the organization id and document id in the URL path, such as /api/organizations/{organizationId}/documents/{documentId}, your self-hosted Jentic One instance lets you write a rule that pins the agent to a single organization, where it can upload, search, and read documents and nothing else. You decide which operations it may call, so destructive ones like the DELETE on a document are left out unless you explicitly add them. Your own rules govern which endpoints and credentials the agent uses at execution time.