[Feature] Add UberLLM chat completion provider template

Open Beginner friendly
  • Is something wrong?
#10,999 1 comment 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
74/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Active
Tech stack
python
Domain
ai, backend

Research direction

Start with the provider templates in astrbot/core/config/default.py, especially the 302.AI entry cited in the issue, and check how the dashboard registers provider icons. Add the UberLLM template with the proposed values and update the provider lists in docs/zh and docs/en if those lists are maintained there. Done means users can select UberLLM and the provider is documented; the issue gives no test file to run.

Written by the indexing model from the issue text.

Description

Feature Description

Add an UberLLM chat-completion provider template next to OpenRouter, 302.AI, SiliconFlow and PPIO in astrbot/core/config/default.py, so users pick it from the provider list instead of filling a custom OpenAI-compatible source by hand.

Disclosure: I work on UberLLM. The PR template asks that new features be discussed with the authors first, so I'm opening this issue before any PR.

Proposed template (same shape as the 302.AI one):

"UberLLM": {
    "id": "uberllm",
    "provider": "uberllm",
    "type": "openai_chat_completion",
    "provider_type": "chat_completion",
    "enable": True,
    "key": [],
    "api_base": "https://api.uberllm.dev/v1",
    "timeout": 120,
    "proxy": "",
    "custom_headers": {},
},

plus the provider icon in the dashboard and a line in docs/zh and docs/en where the provider list is documented, if you want those.

About the service: UberLLM is a hosted OpenAI-compatible API (https://api.uberllm.dev/v1) for GPT, Claude, Gemini, DeepSeek, GLM, Qwen, Kimi and other models, with streaming and tool calls on /v1/chat/completions and a model list at GET /v1/models. It also serves some uncensored models, which roleplay bot users ask for. It is paid: prepaid credit from $5 by card or PayPal, no free tier.

Use Case

A bot owner who wants several model families on one key, without running a gateway themselves, selects UberLLM, pastes the key and picks a model id.

Checklist
  • I have searched the Issue list for related features and confirmed this feature idea has never been proposed.
  • The feature I am suggesting is related to AstrBot itself, not to a specific plugin.
  • I have read and agree to the project's Code of Conduct.
  • (Optional) I am willing to submit a PR to help implement this feature.
Dominant language
Python
Stars
46.4k
Forks
3.4k
Avg merge
1d 10h
Merged PRs (30d)
111

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from AstrBotDevs/AstrBot

All issues in AstrBotDevs/AstrBot

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.