Skip to main content

What is a Session?

A session groups the turns of a single conversation between a user and your AI product. It contains one or more inference results (input/output pairs) and can be evaluated as a whole using conversational metrics. Sessions are created in two ways:
  • Automatically — when you call evaluations.create_single_turn() with a version_id and test_id, a session is created behind the scenes.
  • Manually — when you need to log multi-turn conversations or production data, create a session explicitly with sessions.create().
You can create, view, and manage sessions programmatically using the Galtea SDK.

SDK Integration

Session Service SDK

Manage sessions using the Python SDK

Session Properties

Custom ID
Text
required
The custom ID associated with the session. This is usually a client-side generated ID that identifies the conversation session between a user and a LLM app.
Version
Version
required
The version associated with the session.
Test Case
Test Case
The test case associated with the session. This is typically used for non-production evaluations.
Is Production
Boolean
Indicates whether the session is a production session. This is typically used to differentiate production data from test data. It should be set to True if there is no associated test case.
Context
Text
The context provided to the AI product during the session or ground-truth related context.
Metadata
Object
Additional custom metadata about the session. This can be used to store any relevant information that doesn’t fit into the other fields.
Error
Text
Any error message associated with the session. This is useful for tracking failed sessions or sessions that encountered issues.