Configuration & Ontologies

Endpoints for user configuration and ontology management

User configuration

Store and retrieve per-user configuration for your Cognee Cloud tenant.

POST /api/v1/configuration/store_user_configuration — Store a configuration object.

GET /api/v1/configuration/get_user_configuration/{config_id} — Retrieve a specific configuration by ID. The id is resolved only among the configurations owned by the authenticated user and by the agent users they are the parent of. Any other id — including one that belongs to another account’s configuration — is treated exactly like a missing one: the response is an empty object {} with HTTP 200 (not 404), so a configuration’s existence cannot be probed by id.

GET /api/v1/configuration/get_user_configuration/ — Retrieve all configurations stored by the authenticated user and by the agent users they are the parent of. Each record is of the form {"id", "ownerId", "name", "configuration", "createdAt", "updatedAt"}; ownerId tells the caller’s own records apart from an agent’s. Returns an empty list when there are none.

Ontologies

Ontologies define the structural schema for knowledge graph extraction. They specify which entity types and relationships Cognee should look for during extraction, and an uploaded key can be passed as ontology_key to either cognify or POST /api/v1/remember. See Ontologies for the underlying concept.

GET /api/v1/ontologies — List uploaded ontologies.

POST /api/v1/ontologies — Upload an ontology file.

curl -X POST https://your-tenant.aws.cognee.ai/api/v1/ontologies \
  -H "X-Api-Key: your-key" \
  -F "ontology_key=my_domain_ontology" \
  -F "ontology_file=@my_ontology.owl" \
  -F "description=Domain ontology for entity extraction"

Parameter	Type	Required	Description
ontology_key	string	yes	User-defined identifier for this ontology
ontology_file	file	yes	Ontology file (OWL format)
description	string	no	Human-readable description

DELETE /api/v1/ontologies/{ontology_key} — Delete an uploaded ontology by key.

curl -X DELETE https://your-tenant.aws.cognee.ai/api/v1/ontologies/my_domain_ontology \
  -H "X-Api-Key: your-key"

On success, returns:

{"status": "success", "ontology_key": "my_domain_ontology"}

Status code	Meaning
200	Ontology deleted successfully
400	ontology_key not found
500	Internal error (filesystem)

Ontologies are optional. Without one, Cognee uses its default extraction pipeline. Define an ontology when you need domain-specific entity types or relationships.

LLM helpers

The tenant exposes two LLM helper endpoints that power the Graph Model editor and the Prompt editor in the UI. They are also usable directly with an API key.

POST /api/v1/llm/infer-schema — Propose a JSON schema (entity types and relationships) from sample text and/or uploaded files. The request is multipart/form-data:

curl -X POST https://your-tenant.aws.cognee.ai/api/v1/llm/infer-schema \
  -H "X-Api-Key: your-key" \
  -F "text=Einstein developed general relativity in 1915." \
  -F "data=@sample.pdf" \
  -F 'parameters={"temperature":0.1}'

Form field	Type	Required	Description
text	string	one of text/data	Inline sample text to analyze
data	file(s)	one of text/data	One or more sample files (uses the same loader engine as ingestion)
parameters	JSON string	no	Forwarded to the LLM. Allowed keys: temperature, max_tokens, top_p, seed

The response shape is { "graphSchema": { ... } }, validated against the graph model utility before being returned. The endpoint returns 400 when neither text nor data is supplied, 422 when the LLM output is not valid JSON, and 500 for other inference errors.

POST /api/v1/llm/custom-prompt — Generate a starter cognify prompt for a given graph model. The request is JSON:

curl -X POST https://your-tenant.aws.cognee.ai/api/v1/llm/custom-prompt \
  -H "X-Api-Key: your-key" \
  -H "Content-Type: application/json" \
  -d '{"graph_model": { ... }, "parameters": {}}'

Returns { "customPrompt": "..." }. The same parameters keys (temperature, max_tokens, top_p, seed) are accepted.

Both endpoints live on the tenant API (the per-tenant API base URL shown on the API Keys page), not the platform management API.