auto_rl example uses
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 56/100
- Issue type
- Bug
- Clarity
- Mostly clear
- Activity status
- Quiet
- Tech stack
- python
- Domain
- documentation, machine-learning
Research direction
Start by opening and running examples/auto_rl.ipynb in the linked Colab, then inspect the acompletion call, LiteLLM version, and OpenRouter model configuration. Done means the example follows a documented happy path and clearly records any required provider or model setup.
Written by the indexing model from the issue text.
Description
When trying to run the auto_rl example here the calls to acompletion causes OpenRouter errors:
response = await acompletion(
model=INPUT_GENERATION_MODEL,
messages=messages,
response_format=TrainingDataset,
temperature=1.0,
)
This returns:
[/usr/local/lib/python3.12/dist-packages/litellm/llms/custom_httpx/llm_http_handler.py](https://localhost:8080/#) in _handle_error(self, e, provider_config)
2402
-> 2403 raise provider_config.get_error_class(
2404 error_message=error_text,
OpenRouterException: {"error":{"message":"Provider returned error","code":400,"metadata":{"raw":"{\"code\":400, \"reason\":\"INVALID_REQUEST_BODY\", \"message\":\"model features structured outputs not support\", \"metadata\":{}}","provider_name":"Novita","is_byok":false}},"user_id":"user_xxx"}
I suspect this might be a litellm issue however it seems as though it's fixed there so I'm unsure what's happening. So far I haven't been able to run any of the examples on colab, it may make sense to put some instructions that lead to a happy path with the examples so that folks can get started successfully.
- Dominant language
- Python
- Stars
- 10.8k
- Forks
- 989
- Avg merge
- 6h 29m
- Merged PRs (30d)
- 85
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from OpenPipe/ART
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
enhancement
Difficulty 4/5 3-5 days Newbie friendliness 48/100
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
-
Difficulty 5/5 Over a week Newbie friendliness 35/100
-
Investigate output and gradient variability between matched same-source Qwen TrainerRank actors Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
Similar issues
-
sponsored
Difficulty 2/5 1-3 hours Newbie friendliness 65/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 86/100
Diaoul/subliminal#1382 ·
-
Difficulty 1/5 Under an hour Newbie friendliness 92/100
-
triage/confirmed
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
agentscope-ai/agentscope#2775 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 84/100