Home/Documentation

⌘K

Ontology

The Ontology resource manages domain-specific schemas. Define concepts, relationships, and hierarchies to structure how facts are extracted and organized in your knowledge graph.

POSTclient.ontology.load()

HTTP:POST /v1/ontology

Load or update an ontology domain with concepts and relationships.

Parameters

domainstrRequired

Unique identifier for the ontology domain (e.g., "software_engineering").

namestrRequired

Human-readable name for the ontology.

conceptslist[OntologyConceptRequest | dict]Required

List of concepts to define in the ontology.

descriptionstrOptional

Description of the ontology domain.

relationshipslist[OntologyRelationshipRequest | dict]Optional

Relationships between concepts.

Concept Structure

Concept Fields

concept_idstrRequired

Unique identifier for the concept.

namestrRequired

Human-readable name.

descriptionstrOptional

Description of the concept.

aliaseslist[str]Optional

Alternative names for the concept.

Relationship Structure

Relationship Fields

source_concept_idstrRequired

ID of the source concept.

target_concept_idstrRequired

ID of the target concept.

relationship_typestrRequired

Type of relationship (e.g., "built_with", "is_a", "has_a").

Example

load_ontology.pypython

1from memoair import MemoAir
2
3client = MemoAir()
4
5# Define a software engineering ontology
6client.ontology.load(
7    domain="software_engineering",
8    name="Software Engineering Concepts",
9    description="Common concepts in software development",
10    concepts=[
11        {
12            "concept_id": "python",
13            "name": "Python",
14            "description": "A high-level programming language",
15            "aliases": ["py", "python3"],
16        },
17        {
18            "concept_id": "fastapi",
19            "name": "FastAPI",
20            "description": "Modern Python web framework",
21        },
22        {
23            "concept_id": "pytorch",
24            "name": "PyTorch",
25            "description": "Machine learning framework",
26        },
27        {
28            "concept_id": "web_framework",
29            "name": "Web Framework",
30            "description": "Framework for building web applications",
31        },
32        {
33            "concept_id": "ml_framework",
34            "name": "ML Framework",
35            "description": "Framework for machine learning",
36        },
37    ],
38    relationships=[
39        {
40            "source_concept_id": "fastapi",
41            "target_concept_id": "python",
42            "relationship_type": "built_with",
43        },
44        {
45            "source_concept_id": "pytorch",
46            "target_concept_id": "python",
47            "relationship_type": "built_with",
48        },
49        {
50            "source_concept_id": "fastapi",
51            "target_concept_id": "web_framework",
52            "relationship_type": "is_a",
53        },
54        {
55            "source_concept_id": "pytorch",
56            "target_concept_id": "ml_framework",
57            "relationship_type": "is_a",
58        },
59    ],
60)

GETclient.ontology.get()

HTTP:GET /v1/ontology/{domain}

Retrieve a loaded ontology by domain.

1# Get ontology details
2ontology = client.ontology.get(domain="software_engineering")
3
4print(f"Name: {ontology.name}")
5print(f"Concepts: {len(ontology.concepts)}")
6print(f"Relationships: {len(ontology.relationships)}")

GETclient.ontology.list()

HTTP:GET /v1/ontology

List all loaded ontology domains.

1# List all ontologies
2ontologies = client.ontology.list()
3
4for ont in ontologies:
5    print(f"- {ont.domain}: {ont.name} ({ont.concept_count} concepts)")

GETclient.ontology.stats()

HTTP:GET /v1/ontology/{domain}/stats

Get statistics for a specific ontology.

1stats = client.ontology.stats(domain="software_engineering")
2
3print(f"Domain: {stats.domain}")
4print(f"Concepts: {stats.concept_count}")
5print(f"Relationships: {stats.relationship_count}")

DELETEclient.ontology.delete()

HTTP:DELETE /v1/ontology/{domain}

Delete an ontology domain and all its concepts.

1# Delete an ontology
2client.ontology.delete(domain="software_engineering")

Using Ontologies with Memory

Once an ontology is loaded, you can map extracted facts to ontology concepts during memory ingestion:

ontology_mapping.pypython

1from memoair import MemoAir, Message
2
3client = MemoAir()
4
5# Add memory with ontology mapping
6client.memories.add(
7    group_id="user:john",
8    messages=[
9        Message(
10            content="I've been learning FastAPI for building APIs",
11            role_type="user"
12        ),
13    ],
14    map_to_ontology=True,
15    ontology_domain="software_engineering",
16    ontology_confidence_threshold=0.7,
17)
18
19# The extracted fact "John uses FastAPI" will be linked to:
20# - The "fastapi" concept in the ontology
21# - Which is related to "python" and "web_framework"

Ontology in Tripartite Search

When you enable search_ontology=True in tripartite search, MemoAir includes ontology concepts in the results:

1results = client.search.tripartite(
2    query="What Python frameworks does John know?",
3    user_id="user:john",
4    search_ontology=True,  # Include ontology in search
5)
6
7# Results might include:
8# [user] John uses FastAPI
9# [ontology] FastAPI is a web framework built with Python
10# [ontology] Python is a high-level programming language

Tip: Ontologies help your AI understand domain-specific terminology and relationships, improving search relevance and enabling more accurate fact extraction.