-
Notifications
You must be signed in to change notification settings - Fork 20
Open
Description
Add a CLI command to list available LLM models for the current tenant/region, helping users discover which models they can use for evaluations and other LLM-powered features.
Background
Currently, available models are hardcoded in the SDK's ChatModels class (src/uipath/platform/chat/_llm_gateway_service.py:49-65):
class ChatModels(object):
gpt_4 = "gpt-4"
gpt_4_1106_Preview = "gpt-4-1106-Preview"
gpt_4_32k = "gpt-4-32k"
gpt_4_turbo_2024_04_09 = "gpt-4-turbo-2024-04-09"
gpt_4_vision_preview = "gpt-4-vision-preview"
gpt_4o_2024_05_13 = "gpt-4o-2024-05-13"
gpt_4o_2024_08_06 = "gpt-4o-2024-08-06"
gpt_4o_mini_2024_07_18 = "gpt-4o-mini-2024-07-18"
o3_mini = "o3-mini-2025-01-31"However, model availability varies by:
- Region (US, EU, APAC, etc.)
- Tenant configuration
- AI Trust Layer settings
Users currently have no way to programmatically check which models are available to them, leading to trial-and-error when configuring LLM evaluators.
Metadata
Metadata
Assignees
Labels
No labels