Skip to content

Auto-load model list from /v1/models endpoint #204

@exedev-shelley

Description

@exedev-shelley

Author: quangdz_11
Channel: #llm-gossip
Link: https://discord.com/channels/1405685085923049482/1460426033898721300/1501212392812707921


Description

Auto-populate the model field in Shelley by fetching available models from the /v1/models API endpoint.

Context

From the discussion thread:

  • jra2769: "It would be nice if Shelley auto-filled the 'model' field if the API endpoint reports it supports only one model anyway."
  • quangdz_11: "auto load model list from /v1/models is even better"

Proposed Solution

Instead of requiring manual model selection, Shelley should:

  1. Query the /v1/models endpoint when connecting to an API
  2. Auto-populate the model field based on available models from the endpoint
  3. If only one model is available, auto-select it
  4. If multiple models are available, provide a list for selection

This would improve the user experience by reducing manual configuration steps.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions