Create an Embedding Recorder
MarkovML uses Recorder
to record and store data in your MarkovML account's database. To record embedding-related data, use the EmbeddingRecorder
utility from MarkovML followed by registering it to MarkovML by using register()
so you can view the custom embeddings on the MarkovML UI.
Note
Before registering custom embeddings for a particular dataset, the dataset must first be registered with MarkovML. Visit the Register Dataset page for more information.
Provide the following details to record embedding using theEmbeddingRecorder()
:
name
: Give a unique name to your custom embedding.dataset_id
: Add the dataset_id of the registered dataset you wish to create custom embeddings for.notes
: Notes for future reference. (optional)
Sample Code
import markov
from markov import EmbeddingRecorder
# get dataset by name
data_set = markov.dataset.get_by_name("my_dataset_name")
dataset_id = data_set.ds_id # get dataset id
embedding_recorder = EmbeddingRecorder(
name="Custom embedding name",
dataset_id=dataset_id,
notes="Optional description for this custom embedding "
)
embedding_recorder.register()
Updated 6 days ago
Whatβs Next