Create Collection (Qdrant) (Generative Models)


Creates a new collection in the vector database Qdrant


Creates a new collection in the vector database Qdrant. You need to specify a collection name as well as a size of the embedding vectors for this collection. This size must match the vector size of the embedding vectors you are planning to use when inserting and retrieving documents to and from this collection. You can find the dimension of embedding vectors in the documentation of the embedding operators. In addition, all embedding operators also print the dimension of the embeddings to the logs when executed.


  • connection (Connection)

    A Dictionary Connection for a Qdrant vector database.


  • data (Data Table)

    A small data set containing status information about this creation request.

  • connection (Connection)

    The input connection which is passed through here as output.


  • name The name of the new collection. Range:
  • vector_size The vector size of all documents in this collection. Must match the dimension of the embedding vectors which will be provided during inserting or retrieving documents to and from this collection. Range:
  • distance The distance function used for all similarity calculations for document retrieval. Range:
  • conda_environment The conda environment used for this task. Please refer to the extension documentation for additional details on this and on version requirements for Python and all used packages in this environment. Range:

Tutorial Processes

Create Collection in Qdrant

This tutorial process creates a new collection with the specified name and vector size in a Qdrant vector database. The database connection must be delivered as input for this tutorial to work. The connection must be a Dictionary Connection with the keys 'host', 'port', and (optional) 'api_key'.