Skip to main content
Version: Next

Qdrant

Qdrant source connector

Description​

Qdrant is a high-performance vector search engine and vector database.

This connector can be used to read data from a Qdrant collection.

Options​

nametyperequireddefault value
collection_namestringyes-
schemaconfigyes-
hoststringnolocalhost
portintno6334
api_keystringno-
use_tlsintnofalse
common-optionsno-

collection_name [string]​

The name of the Qdrant collection to read data from.

schema [config]​

The schema of the table to read data into.

Eg:

schema = {
fields {
age = int
address = string
some_vector = float_vector
}
}

Each entry in Qdrant is called a point.

The float_vector type columns are read from the vectors of each point, others are read from the JSON payload associated with the point.

If a column is marked as primary key, the ID of the Qdrant point is written into it. It can be of type "string" or "int". Since Qdrant only allows positive integers and UUIDs as point IDs.

If the collection was created with a single default/unnamed vector, use default_vector as the vector name.

schema = {
fields {
age = int
address = string
default_vector = float_vector
}
}

The ID of the point in Qdrant will be written into the column which is marked as the primary key. It can be of type int or string.

host [string]​

The host name of the Qdrant instance. Defaults to "localhost".

port [int]​

The gRPC port of the Qdrant instance.

api_key [string]​

The API key to use for authentication if set.

use_tls [bool]​

Whether to use TLS(SSL) connection. Required if using Qdrant cloud(https).

common options​

Source plugin common parameters, please refer to Source Common Options for details.