Create Vector Database Collection
POST
/api/v3/organizations/{organisation}/ai/vector-db/collections
const url = 'https://dashboard.quantcdn.io/api/v3/organizations/example/ai/vector-db/collections';const options = { method: 'POST', headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'}, body: '{"name":"product-documentation","description":"Product user guides and API documentation","embeddingModel":"amazon.titan-embed-text-v2:0","dimensions":1024}'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request POST \ --url https://dashboard.quantcdn.io/api/v3/organizations/example/ai/vector-db/collections \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data '{ "name": "product-documentation", "description": "Product user guides and API documentation", "embeddingModel": "amazon.titan-embed-text-v2:0", "dimensions": 1024 }'Creates a new vector database collection (knowledge base category) for semantic search. Collections store documents with embeddings for RAG (Retrieval Augmented Generation). * * Use Cases: * - Product documentation (‘docs’) * - Company policies (‘policies’) * - Support knowledge base (‘support’) * - Technical specifications (‘specs’)
Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Path Parameters
Section titled “Path Parameters”organisation
required
string
The organisation ID
Request Bodyrequired
Section titled “Request Bodyrequired”Media typeapplication/json
object
name
required
Collection name (used for reference)
string
Example
product-documentationdescription
string
Example
Product user guides and API documentationembeddingModel
required
Embedding model to use. Supported: amazon.titan-embed-text-v2:0, cohere.embed-english-v3, cohere.embed-multilingual-v3
string
Example
amazon.titan-embed-text-v2:0dimensions
Embedding dimensions (default: 1024)
integer
Example
1024Responses
Section titled “Responses”Collection created successfully
Media typeapplication/json
object
success
boolean
collection
object
collectionId
string format: uuid
name
string
description
string
embeddingModel
string
dimensions
integer
message
string
Example
{ "success": true, "message": "Collection created successfully"}Invalid request parameters
Access denied
Collection with this name already exists
Failed to create collection