Create a new vector store for semantic search and RAG (Retrieval Augmented Generation).
Vector stores enable semantic search across your documents. Upload files, and the AI can search and reference them in responses.
organization_id string required
The unique identifier of the organization.
name string required
Name of the vector store.
description string optional
Description of the vector store's purpose or contents.
access_mode string optional ยท Defaults to organization
Access control level:
public- Everyone can accessorganization- All organization membersdepartment- Specific departments onlyprivate- Only creator and specified users
access_departments array optional
Department IDs that can access (when access_mode is department).
access_users array optional
User IDs that can access (when access_mode is private).
flowplate_project_id string optional
Associate this vector store with a Flowplate project.
flow_id string optional
Associate this vector store with a specific flow.
- Bash
- Python
- Python
- JavaScript
curl -X POST "https://api.aitronos.com/v1/organizations/org_abc123/vector-stores" \
-H "X-API-Key: $FREDDY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"name": "Product Documentation",
"description": "Knowledge base for product support"
}'Response:
{
"id": "vs_abc123",
"object": "vector_store",
"name": "Product Documentation",
"description": "Knowledge base for product support",
"organization_id": "org_abc123",
"created_by": "usr_alice123",
"access_mode": "organization",
"access_departments": [],
"access_users": [],
"file_count": 0,
"total_size_bytes": 0,
"status": "active",
"created_at": "2025-11-13T10:30:00Z",
"updated_at": "2025-11-13T10:30:00Z"
}