Qdrant: Create new collection

qdrant_create_new_collection establishes a connection with a qdrant instance and creates a new collection. '

Usage

qdrant_create_new_collection(
  conn,
  collection_name = NA_character_,
  vectors = list(size = 384, distance = "Cosine")
)

Arguments

conn

a connection object created by get_qdrant_connection()

collection_name

the name of the collection you want to create. Defaults to NA.

vectors

a R list object that needs to contain 'size' and 'distance'. Defaults to size=384 and distance='Cosine' This needs to be adapted to the embedding model you use. Different models have different resulting vector sizes.

Details

Creates a new collection for vector embeddings. You can customize the size of embeddings needed and the type of distance for similarity search. If a collection already exists with the same name it will throw an error.

Examples

conn <- get_qdrant_connection()
#> → Connection to Qdrant confirmed
qdrant_create_new_collection(conn, collection_name="story_of_my_life")
#> → Collection story_of_my_life was just created on the qdrant instance.
qdrant_delete_collection(conn, collection_name="story_of_my_life")
#> → Collection story_of_my_life was just deleted on the qdrant instance.