Model Metadata

Seldon Enterprise Platform supports the storage and management of model metadata. This includes project name, artifact URI, ML runtime, and prediction schema, amongst other things.

Model metadata is dependent on Postgres. For more information on configuring Postgres with Seldon Enterprise Platform, see the installation instructions.

You can create and manage model metadata through the Enterprise Platform UI and API. Enterprise Platform will also watch for deployments in the Kubernetes cluster and sync this information into the metadata store. In this case, the Platform will only populate basic information, but this can then be enriched via the UI and API as with any other model metadata.

Queries

Seldon Enterprise Platform provides an advanced query language that allows you to make sophisticated search queries over your model metadata.

Simple fields can be compared using SQL-like comparison and partial match operators. Nested fields can be compared by first using index notation to extract simple fields. More complex expressions can be formed with the AND and OR operators and parentheses. Note that the AND and OR operators are treated as having equal precedence.

Operator	Meaning
=	Equal
!=	Not equal
>	Greater than
<	Less than
>=	Greater than or equal to
<=	Less than or equal to
%	Like -- partial match
AND	Conjunction
OR	Disjunction
(...)	Subexpression for ...

Field names and operators are not case-sensitive. Field values are case-sensitive, however, and should not be wrapped in quotes. The list of valid fields to query is:

Field name	Type	Description
URI	Simple	String
name	Simple	String
version	Simple	String, e.g. 1.0, v2, dev
project	Simple	String
artifact_type	Simple	One of ALIBI_DETECT, ALIBI_EXPLAIN, CUSTOM, HUGGINGFACE, MLFLOW, MLSERVER_PYTHON, ONNX, PYTORCH, SKLEARN, TENSORFLOW, TENSORRT, TRITON_PYTHON, UNKNOWN, XGBOOST
task_type	Simple	String, e.g. classification or object-detection
tags	Nested	Map of string to string
metrics	Nested	Map of string to number

Examples

name % iris

name=iris AND version=2.0

(name=iris AND version=2.0) OR version=3.0

metrics[metricName] > 1.0 AND tags[tagKey] != someValue

API

Using the model metadata API, you can specify a string query the same way you would in the UI, e.g.

<yourSeldonDomain>/seldon-deploy/api/v1alpha1/model/metadata?query=(version=1.0)