Extract entities and relations from documents
Reads `text_fields` off each of `document_ids`, asks a model for the named entities it mentions and the relations between them, and upserts them: an entity already known by the exact same `name` gets this document added to its `source_doc_ids` instead of a duplicate row. A new name that doesn't match exactly is still resolved semantically against this collection's existing entities of the same `type` by embedding similarity — a close enough match (e.g. "De Walt" against "DeWalt") is folded in as an `alias` rather than creating a near-duplicate entity; only a name with no close match becomes a new entity. A relation already known between the same two resolved entities is left as-is. A second model call then extracts claims ("covariates") about that document's resolved entities — specific assertions like a capability, certification, or limitation, distinct from the relations between entities — see `GraphClaim`. Synchronous; keep `document_ids` small (50 at most) and call it again for the next batch. Entity extraction is the expensive step of this feature — nothing runs on a schedule, this is the only way new entities and claims appear.
Full-key operation
Reads text_fields off each of document_ids, asks a model for the named entities it mentions and the relations between them, and upserts them: an entity already known by the exact same name gets this document added to its source_doc_ids instead of a duplicate row. A new name that doesn't match exactly is still resolved semantically against this collection's existing entities of the same type by embedding similarity — a close enough match (e.g. "De Walt" against "DeWalt") is folded in as an alias rather than creating a near-duplicate entity; only a name with no close match becomes a new entity. A relation already known between the same two resolved entities is left as-is. A second model call then extracts claims ("covariates") about that document's resolved entities — specific assertions like a capability, certification, or limitation, distinct from the relations between entities — see GraphClaim. Synchronous; keep document_ids small (50 at most) and call it again for the next batch. Entity extraction is the expensive step of this feature — nothing runs on a schedule, this is the only way new entities and claims appear.
Authorization
api_key_header Every request carries an organization API key. A key has one of two scopes. A full key reaches every operation in this document and belongs on your server. A search key is the one to ship in a browser widget or a storefront page: it reaches only the operations marked x-nova-key-scope: search — searching, federated search, recommendations, event ingestion, and the visitor-facing AI operations (semantic and image search, voice transcription and voice search, assistant chat, and the visitor's own conversation). It cannot write documents or read or change configuration; any other operation answers 403. AI operations are paid in credits from the organization's wallet whichever key calls them (402 when the balance runs out), and a search key needs X-NOVA-SESSION-ID on them: the session is what a conversation belongs to, and what the per-session allowance (429) is counted against. A key of either scope may additionally carry restrictions set in the console: an allowlist of collections (403 elsewhere), a forced filter_by per collection that is ANDed into every search (document-level access control), an allowlist of fields (include_fields is limited to it and a request naming any other field in query_by, facet_by, sort_by, filter_by or highlight_fields answers 400), an IP/CIDR allowlist and an Origin/Referer allowlist (403), and a per-key rate limit (429 with Retry-After).
In: header
Path Parameters
The name of the collection
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
application/json
application/json
application/json
curl -X POST "https://example.com/collections/string/graph/entities/generate" \ -H "Content-Type: application/json" \ -d '{ "document_ids": [ "string" ], "text_fields": [ "string" ] }'{ "examined": 0, "entities_created": 0, "entities_updated": 0, "edges_created": 0, "claims_created": 0, "entities": [ { "id": "string", "collection": "string", "name": "string", "type": "string", "description": "string", "aliases": [ "string" ], "source_doc_ids": [ "string" ], "community_id": "string", "created_at": 0, "updated_at": 0 } ], "claims": [ { "id": "string", "collection": "string", "subject_id": "string", "claim_type": "string", "object": "string", "status": "confirmed", "description": "string", "source_doc_id": "string", "created_at": 0 } ]}