​

Collections

​

Why Use Collections?

• Separate contexts: Keep work, personal, and project memories distinct
• Targeted search: Search only within relevant collections
• Access control: Different API keys can have different collection permissions
• Multi-tenancy: Isolate data for different users or customers

​

Creating Collections

from nebula import Nebula
nebula = Nebula(api_key="your-api-key")

collection = nebula.create_collection(
    name="Research Papers",
    description="Academic research documents",
    metadata={"category": "academic"}
)

​

Storing Memories in Collections

nebula.store_memory({
    "collection_id": collection.id,
    "content": "Q4 planning meeting notes",
    "metadata": {"type": "meeting"}
})

​

Searching Within Collections

# Search specific collection
results = nebula.search(query="deadlines", collection_ids=["Work"])

# Search multiple collections
results = nebula.search(query="notes", collection_ids=["Work", "Personal"])

# Search all accessible collections
results = nebula.search(query="important")

​

Managing Collections

collections = nebula.list_collections(limit=50)
work_collections = nebula.list_collections(name="Work")

collection = nebula.get_collection(collection_id)

nebula.update_collection(
    collection_id=collection.id,
    name="Updated Name",
    description="New description"
)

nebula.delete_collection(collection_id)

​

Common Patterns

​

Best Practices

1. Use descriptive names - customer_support not collection_1
2. Leverage metadata - Store organizational info in collection metadata
3. Specify collection_ids for targeted searches - Faster, scoped searches
4. Plan for scale - Consider collection strategy early

​

Next Steps

• Memory Operations - Store and search memories
• Metadata Filtering - Advanced filtering