Skip to main content
POST
/
api
/
r2r
/
v3
/
documents
/
{id}
/
extract
Extract entities and relationships
curl --request POST \
  --url https://api.intelligence.io.solutions/api/r2r/v3/documents/{id}/extract \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "settings": {
    "graph_extraction_prompt": "graph_extraction",
    "graph_entity_description_prompt": "graph_entity_description",
    "entity_types": "<string>",
    "relation_types": "<string>",
    "chunk_merge_count": 2,
    "max_knowledge_relationships": 100,
    "max_description_input_length": 65536,
    "generation_config": {},
    "automatic_deduplication": false
  },
  "run_with_orchestration": true
}
'
{
  "results": {
    "message": "message"
  }
}
The entities and relationships extraction process involves:
  1. Parsing documents into semantic chunks
  2. Extracting entities and relationships using LLMs
  3. Storing the created entities and relationships in the knowledge graph
  4. Preserving the document’s metadata and content, and associating the elements with collections the document belongs to

Authorizations

​
Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Path Parameters

​
id
string
required

The ID of the document to extract entities and relationships from.

Body

application/json
​
settings
object

Settings for the entities and relationships extraction process.

​
run_with_orchestration
boolean

Whether to run the entities and relationships extraction process with orchestration.

Response

200

​
results
object