API for managing enterprise context and memory items with authentication and user-specific data.
API for managing enterprise context and memory items with authentication and user-specific data.
This API supports three authentication methods:
X-API-Key headerX-API-Key: <your-api-key>X-Session-Token headerX-Session-Token: <your-session-token>Authorization headerAuthorization: Bearer <token>All endpoints require one of these authentication methods.
curl -i -X GET \
'https://memory.papr.ai/v1/sync/delta?cursor=string&include_embeddings=false&limit=200&workspace_id=string' \
-H 'X-API-Key: YOUR_API_KEY_HERE'{}
Telemetry proxy endpoint for anonymous OSS adoption tracking.
This endpoint receives telemetry events from OSS installations and forwards them to Amplitude using Papr's API key (which stays secure on the server).
Privacy:
Opt-in: Users must explicitly enable telemetry in their OSS installation.
Request Body:
{
"events": [
{
"event_name": "memory_created",
"properties": {
"type": "text",
"has_metadata": true
},
"user_id": "hashed_user_id",
"timestamp": 1234567890000
}
],
"anonymous_id": "session_id"
}List of telemetry events to track
Event name (e.g., 'memory_created', 'search_performed')
Event properties (will be anonymized)
Event properties (will be anonymized)
Anonymous user ID (hashed)
Anonymous user ID (hashed)
Anonymous user ID (hashed)
curl -i -X POST \
https://memory.papr.ai/v1/telemetry/events \
-H 'Content-Type: application/json' \
-d '{
"events": [
{
"event_name": "string",
"properties": {},
"user_id": "string",
"timestamp": 0
}
],
"anonymous_id": "string"
}'{ "success": true, "events_received": 0, "events_processed": 0, "message": "string" }
Upload and process documents using the pluggable architecture.
Authentication Required: Bearer token or API key
Supported Providers: TensorLake.ai, Reducto AI, Gemini Vision (fallback)
Features:
Preferred provider for document processing.
Preferred provider for document processing.
JSON-encoded unified processing policy (transform_embedding, graph incl. link_to, consent, risk, acl). Applies to all chunks from this document.
JSON-encoded unified processing policy (transform_embedding, graph incl. link_to, consent, risk, acl). Applies to all chunks from this document.
JSON-encoded unified processing policy (transform_embedding, graph incl. link_to, consent, risk, acl). Applies to all chunks from this document.
Your application's user identifier. This is the primary way to identify users. Also accepts legacy 'end_user_id'.
Your application's user identifier. This is the primary way to identify users. Also accepts legacy 'end_user_id'.
Your application's user identifier. This is the primary way to identify users. Also accepts legacy 'end_user_id'.
DEPRECATED: Internal Papr Parse user ID. Most developers should use external_user_id.
DEPRECATED: Internal Papr Parse user ID. Most developers should use external_user_id.
DEPRECATED: Internal Papr Parse user ID. Most developers should use external_user_id.
DEPRECATED: Use 'policy' instead. JSON-encoded memory policy. Includes mode ('auto'/'manual'), schema_id, node_constraints (applied in auto mode when present), and OMO fields (consent, risk, acl).
DEPRECATED: Use 'policy' instead. JSON-encoded memory policy. Includes mode ('auto'/'manual'), schema_id, node_constraints (applied in auto mode when present), and OMO fields (consent, risk, acl).
DEPRECATED: Use 'policy' instead. JSON-encoded memory policy. Includes mode ('auto'/'manual'), schema_id, node_constraints (applied in auto mode when present), and OMO fields (consent, risk, acl).
DEPRECATED: Use policy.transform_embedding instead. If True, applies holographic neural transforms and stores in holographic collection.
DEPRECATED: Use policy.transform_embedding.domain_id instead. Frequency schema for holographic embedding (e.g. 'cosqa', 'scifact'). Required when enable_holographic=True. Call GET /v1/frequencies to see available schemas.
DEPRECATED: Use policy.transform_embedding.domain_id instead. Frequency schema for holographic embedding (e.g. 'cosqa', 'scifact'). Required when enable_holographic=True. Call GET /v1/frequencies to see available schemas.
DEPRECATED: Use policy.transform_embedding.domain_id instead. Frequency schema for holographic embedding (e.g. 'cosqa', 'scifact'). Required when enable_holographic=True. Call GET /v1/frequencies to see available schemas.
curl -i -X POST \
https://memory.papr.ai/v1/document \
-H 'Authorization: Bearer <YOUR_JWT_HERE>' \
-H 'Content-Type: multipart/form-data' \
-F file=string \
-F preferred_provider=gemini \
-F hierarchical_enabled=true \
-F schema_id=string \
-F graph_override=string \
-F property_overrides=string \
-F memory_policy=string \
-F policy=string \
-F namespace_id=string \
-F external_user_id=string \
-F user_id=string \
-F webhook_url=string \
-F webhook_secret=string \
-F enable_holographic=false \
-F frequency_schema_id=string \
-F metadata=stringDocument upload started
Human-readable status message
Human-readable status message
Human-readable status message
Error message if failed
Error message if failed
Error message if failed
Additional error details or context
Additional error details or context
Additional error details or context
Status and progress of the document upload
Post ID in Parse Server (user-facing page ID)
Post ID in Parse Server (user-facing page ID)
Post ID in Parse Server (user-facing page ID)
Processing status type
Processing status type
Processing status type
{ "code": 200, "status": "success", "message": "string", "error": "string", "details": {}, "document_status": { "progress": 0, "current_page": 0, "total_pages": 0, "current_filename": "string", "upload_id": "string", "page_id": "string", "status_type": "processing", "error": "string" }, "memory_items": [ { … } ], "memories": [ { … } ] }