Start using gyaan vector database locally within 15 minutes
Explanation
create()
class method creates a new VectorStorage
object, that you can use later in your code. It assigns a random UUIDv6 as the store_id to this object, for time-stamped uniqueness.create()
also allows you to specify additional metadata information like title, description, keywords, and even a custom store_id, which is useful when you want to attach a vector store to a particular AI Agent or your app’s user via their ID.numpy
but in practise you would be using the embedding provider of your choice.
get_vectors
method, which returns up to 100 vectors by default
top_k
: Maximum number of desired search results. Default value is 10centroid_search_radius
: Maximum number of clusters to filter for performing full search. Default value is 3distance_metric
: Currently, we support “euclidean” and “cosine”. Default value is “cosine”.