Milvus is an open-source, distributed vector database designed for similarity search and analytics on large-scale vector data. The connection to Milvus is based on the pymilvus library.
To use Milvus you must have a URI to a running Milvus instance. Here are the instructions to spin up a local instance.
If you are running it locally, the Milvus instance should be running on
http://localhost:19530. Please be sure that the Milvus version is >= 2.3.0. Below are values that the Milvus integration uses:
MILVUS_URI is the URI of the Milvus instance (which would be
http://localhost:19530when running locally). This value is required
MILVUS_USER is the name of the user for the Milvus instance.
MILVUS_PASSWORD is the password of the user for the Milvus instance.
MILVUS_DB_NAME is the name of the database to be used. This will default to the default database if not provided.
MILVUS_TOKEN is the authorization token for the Milvus instance.
The above values can either be set via the
SET statement, or in the os environment fields “MILVUS_URI”, “MILVUS_USER”, “MILVUS_PASSWORD”, “MILVUS_DB_NAME”, and “MILVUS_TOKEN”
SET MILVUS_URI = 'http://localhost:19530';
CREATE INDEX index_name ON table_name (data) USING MILVUS;