Skip to main content

Knowledge Graph

Ask the configured LLM to extract a knowledge graph — entities and the relations between them — from the input. Useful for building a queryable representation of unstructured documents.

Pre-requisite: Install an AI provider application from Profile > {Organization} > Applications.

Parameters​

Provider—REQUIRED
Configured AI application.
Model

Model identifier from the selected provider. Defaults to the provider's recommended model when left empty.

System Context

System prompt prepended to every call. Use it to set extraction rules (e.g. relation vocabulary, entity types).

JSON Path

JSON path expression selecting which subtree of the input to extract from. Leave empty to feed the whole input to the model.

Domain Knowledge

Domain-specific knowledge sent alongside each call (e.g. "These are pharmaceutical clinical trial reports — entities of interest are drugs, conditions, dosages, outcomes."). Helps the model produce a relevant graph.

Input​

File or JSON—REQUIRED

Source content — either a JSONL file or an inline JSON record.

Output​

Graph

JSON document containing the extracted entities and relations.