Skip to main content

Create Collection

POST 
/api/v1/admin/collections

Create a Qdrant collection for vector storage.

This endpoint allows you to create collections with custom vector dimensions and distance metrics before indexing data.

Common vector sizes:

  • 384: sentence-transformers/all-MiniLM-L6-v2
  • 768: BERT, sentence-transformers/all-mpnet-base-v2
  • 1536: OpenAI text-embedding-ada-002
  • 3072: OpenAI text-embedding-3-large

Distance metrics:

  • Cosine: Best for normalized embeddings (most common)
  • Euclid: Euclidean distance
  • Dot: Dot product (for pre-normalized vectors)

Request​

Responses​

Successful Response