Create a new graph based on document contents.
The graph is created asynchronously. A stub graph record is returned with
status = "processing" while a background task extracts entities and
relationships.
Request model for creating a graph
Name of the graph to create
Optional metadata filters to determine which documents to include
Optional list of specific document IDs to include
Optional customizations for entity extraction and resolution prompts
{
"entity_extraction": {
"examples": [{ "label": "Example", "type": "ENTITY" }],
"prompt_template": "Extract entities from the following text: {content}\n{examples}"
}
}Optional folder scope for the operation. Accepts a single folder name or a list of folder names.
Optional end-user scope for the operation
Successful Response
Represents a knowledge graph