API & SDKsCollections

Extract entities and relationships

Extracts entities and relationships from a document.

The entities and relationships extraction process involves:

  1. Parsing documents into semantic chunks
  2. Extracting entities and relationships using LLMs

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

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

Headers

X-API-KeystringRequired

Query parameters

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

Request

Settings for the entities and relationships extraction process.
graph_extraction_promptstringOptionalDefaults to graph_extraction
The prompt to use for knowledge graph extraction.
graph_entity_description_promptstringOptionalDefaults to graph_entity_description
The prompt to use for entity description generation.
entity_typeslist of stringsOptional
The types of entities to extract.
relation_typeslist of stringsOptional
The types of relations to extract.
chunk_merge_countintegerOptionalDefaults to 2
The number of extractions to merge into a single graph extraction.
max_knowledge_relationshipsintegerOptionalDefaults to 100
The maximum number of knowledge relationships to extract from each chunk.
max_description_input_lengthintegerOptionalDefaults to 65536
The maximum length of the description for a node in the graph.
generation_configobjectOptional
Configuration for text generation during graph enrichment.
automatic_deduplicationbooleanOptionalDefaults to false
Whether to automatically deduplicate entities.

Response

Successful Response
resultsobject

Errors